Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures

Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Zhang, Xingyu [verfasserIn] Zhang, Xiongwei [verfasserIn] Liu, Wei [verfasserIn] Zou, Xia [verfasserIn] Sun, Meng [verfasserIn] Zhao, Jian [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Schlagwörter:	Automatic speaker verification Spoofing countermeasures Adversarial example Joint attack Waveform gradients

Übergeordnetes Werk:	Enthalten in: Engineering applications of artificial intelligence - Amsterdam [u.a.] : Elsevier Science, 1988, 116
Übergeordnetes Werk:	volume:116

DOI / URN:	10.1016/j.engappai.2022.105469

Katalog-ID:	ELV008696357

Internformat


LEADER	01000caa a22002652 4500
001	ELV008696357
003	DE-627
005	20230524152201.0
007	cr uuu---uuuuu
008	230509s2022 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.1016/j.engappai.2022.105469 \|2 doi
035			\|a (DE-627)ELV008696357
035			\|a (ELSEVIER)S0952-1976(22)00459-6
040			\|a DE-627 \|b ger \|c DE-627 \|e rda
041			\|a eng
082	0	4	\|a 004 \|q DE-600
084			\|a 50.23 \|2 bkl
084			\|a 54.72 \|2 bkl
100	1		\|a Zhang, Xingyu \|e verfasserin \|0 (orcid)0000-0003-0783-684X \|4 aut
245	1	0	\|a Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures
264		1	\|c 2022
336			\|a nicht spezifiziert \|b zzz \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated.
650		4	\|a Automatic speaker verification
650		4	\|a Spoofing countermeasures
650		4	\|a Adversarial example
650		4	\|a Joint attack
650		4	\|a Waveform gradients
700	1		\|a Zhang, Xiongwei \|e verfasserin \|4 aut
700	1		\|a Liu, Wei \|e verfasserin \|4 aut
700	1		\|a Zou, Xia \|e verfasserin \|4 aut
700	1		\|a Sun, Meng \|e verfasserin \|4 aut
700	1		\|a Zhao, Jian \|e verfasserin \|0 (orcid)0000-0002-3508-756X \|4 aut
773	0	8	\|i Enthalten in \|t Engineering applications of artificial intelligence \|d Amsterdam [u.a.] : Elsevier Science, 1988 \|g 116 \|h Online-Ressource \|w (DE-627)308447832 \|w (DE-600)1502275-4 \|w (DE-576)094752524 \|x 0952-1976 \|7 nnns
773	1	8	\|g volume:116
912			\|a GBV_USEFLAG_U
912			\|a SYSFLAG_U
912			\|a GBV_ELV
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_31
912			\|a GBV_ILN_32
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_74
912			\|a GBV_ILN_90
912			\|a GBV_ILN_95
912			\|a GBV_ILN_100
912			\|a GBV_ILN_101
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_150
912			\|a GBV_ILN_151
912			\|a GBV_ILN_224
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_702
912			\|a GBV_ILN_2003
912			\|a GBV_ILN_2004
912			\|a GBV_ILN_2005
912			\|a GBV_ILN_2008
912			\|a GBV_ILN_2010
912			\|a GBV_ILN_2011
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2015
912			\|a GBV_ILN_2020
912			\|a GBV_ILN_2021
912			\|a GBV_ILN_2025
912			\|a GBV_ILN_2027
912			\|a GBV_ILN_2034
912			\|a GBV_ILN_2038
912			\|a GBV_ILN_2044
912			\|a GBV_ILN_2048
912			\|a GBV_ILN_2049
912			\|a GBV_ILN_2050
912			\|a GBV_ILN_2056
912			\|a GBV_ILN_2059
912			\|a GBV_ILN_2061
912			\|a GBV_ILN_2064
912			\|a GBV_ILN_2065
912			\|a GBV_ILN_2068
912			\|a GBV_ILN_2088
912			\|a GBV_ILN_2111
912			\|a GBV_ILN_2112
912			\|a GBV_ILN_2113
912			\|a GBV_ILN_2118
912			\|a GBV_ILN_2122
912			\|a GBV_ILN_2129
912			\|a GBV_ILN_2143
912			\|a GBV_ILN_2147
912			\|a GBV_ILN_2148
912			\|a GBV_ILN_2152
912			\|a GBV_ILN_2153
912			\|a GBV_ILN_2190
912			\|a GBV_ILN_2336
912			\|a GBV_ILN_2470
912			\|a GBV_ILN_2507
912			\|a GBV_ILN_2522
912			\|a GBV_ILN_4035
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4046
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4242
912			\|a GBV_ILN_4251
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4326
912			\|a GBV_ILN_4333
912			\|a GBV_ILN_4334
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4393
936	b	k	\|a 50.23 \|j Regelungstechnik \|j Steuerungstechnik
936	b	k	\|a 54.72 \|j Künstliche Intelligenz
951			\|a AR
952			\|d 116

Indexfelder

author_variant	x z xz x z xz w l wl x z xz m s ms j z jz
matchkey_str	article:09521976:2022----::aeomeeavrailxmlgnrtofronatcsgisbtatmtcpaevrfc
hierarchy_sort_str	2022
bklnumber	50.23 54.72
publishDate	2022
allfields	10.1016/j.engappai.2022.105469 doi (DE-627)ELV008696357 (ELSEVIER)S0952-1976(22)00459-6 DE-627 ger DE-627 rda eng 004 DE-600 50.23 bkl 54.72 bkl Zhang, Xingyu verfasserin (orcid)0000-0003-0783-684X aut Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated. Automatic speaker verification Spoofing countermeasures Adversarial example Joint attack Waveform gradients Zhang, Xiongwei verfasserin aut Liu, Wei verfasserin aut Zou, Xia verfasserin aut Sun, Meng verfasserin aut Zhao, Jian verfasserin (orcid)0000-0002-3508-756X aut Enthalten in Engineering applications of artificial intelligence Amsterdam [u.a.] : Elsevier Science, 1988 116 Online-Ressource (DE-627)308447832 (DE-600)1502275-4 (DE-576)094752524 0952-1976 nnns volume:116 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 50.23 Regelungstechnik Steuerungstechnik 54.72 Künstliche Intelligenz AR 116
spelling	10.1016/j.engappai.2022.105469 doi (DE-627)ELV008696357 (ELSEVIER)S0952-1976(22)00459-6 DE-627 ger DE-627 rda eng 004 DE-600 50.23 bkl 54.72 bkl Zhang, Xingyu verfasserin (orcid)0000-0003-0783-684X aut Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated. Automatic speaker verification Spoofing countermeasures Adversarial example Joint attack Waveform gradients Zhang, Xiongwei verfasserin aut Liu, Wei verfasserin aut Zou, Xia verfasserin aut Sun, Meng verfasserin aut Zhao, Jian verfasserin (orcid)0000-0002-3508-756X aut Enthalten in Engineering applications of artificial intelligence Amsterdam [u.a.] : Elsevier Science, 1988 116 Online-Ressource (DE-627)308447832 (DE-600)1502275-4 (DE-576)094752524 0952-1976 nnns volume:116 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 50.23 Regelungstechnik Steuerungstechnik 54.72 Künstliche Intelligenz AR 116
allfields_unstemmed	10.1016/j.engappai.2022.105469 doi (DE-627)ELV008696357 (ELSEVIER)S0952-1976(22)00459-6 DE-627 ger DE-627 rda eng 004 DE-600 50.23 bkl 54.72 bkl Zhang, Xingyu verfasserin (orcid)0000-0003-0783-684X aut Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated. Automatic speaker verification Spoofing countermeasures Adversarial example Joint attack Waveform gradients Zhang, Xiongwei verfasserin aut Liu, Wei verfasserin aut Zou, Xia verfasserin aut Sun, Meng verfasserin aut Zhao, Jian verfasserin (orcid)0000-0002-3508-756X aut Enthalten in Engineering applications of artificial intelligence Amsterdam [u.a.] : Elsevier Science, 1988 116 Online-Ressource (DE-627)308447832 (DE-600)1502275-4 (DE-576)094752524 0952-1976 nnns volume:116 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 50.23 Regelungstechnik Steuerungstechnik 54.72 Künstliche Intelligenz AR 116
allfieldsGer	10.1016/j.engappai.2022.105469 doi (DE-627)ELV008696357 (ELSEVIER)S0952-1976(22)00459-6 DE-627 ger DE-627 rda eng 004 DE-600 50.23 bkl 54.72 bkl Zhang, Xingyu verfasserin (orcid)0000-0003-0783-684X aut Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated. Automatic speaker verification Spoofing countermeasures Adversarial example Joint attack Waveform gradients Zhang, Xiongwei verfasserin aut Liu, Wei verfasserin aut Zou, Xia verfasserin aut Sun, Meng verfasserin aut Zhao, Jian verfasserin (orcid)0000-0002-3508-756X aut Enthalten in Engineering applications of artificial intelligence Amsterdam [u.a.] : Elsevier Science, 1988 116 Online-Ressource (DE-627)308447832 (DE-600)1502275-4 (DE-576)094752524 0952-1976 nnns volume:116 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 50.23 Regelungstechnik Steuerungstechnik 54.72 Künstliche Intelligenz AR 116
allfieldsSound	10.1016/j.engappai.2022.105469 doi (DE-627)ELV008696357 (ELSEVIER)S0952-1976(22)00459-6 DE-627 ger DE-627 rda eng 004 DE-600 50.23 bkl 54.72 bkl Zhang, Xingyu verfasserin (orcid)0000-0003-0783-684X aut Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated. Automatic speaker verification Spoofing countermeasures Adversarial example Joint attack Waveform gradients Zhang, Xiongwei verfasserin aut Liu, Wei verfasserin aut Zou, Xia verfasserin aut Sun, Meng verfasserin aut Zhao, Jian verfasserin (orcid)0000-0002-3508-756X aut Enthalten in Engineering applications of artificial intelligence Amsterdam [u.a.] : Elsevier Science, 1988 116 Online-Ressource (DE-627)308447832 (DE-600)1502275-4 (DE-576)094752524 0952-1976 nnns volume:116 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 50.23 Regelungstechnik Steuerungstechnik 54.72 Künstliche Intelligenz AR 116
language	English
source	Enthalten in Engineering applications of artificial intelligence 116 volume:116
sourceStr	Enthalten in Engineering applications of artificial intelligence 116 volume:116
format_phy_str_mv	Article
bklname	Regelungstechnik Steuerungstechnik Künstliche Intelligenz
institution	findex.gbv.de
topic_facet	Automatic speaker verification Spoofing countermeasures Adversarial example Joint attack Waveform gradients
dewey-raw	004
isfreeaccess_bool	false
container_title	Engineering applications of artificial intelligence
authorswithroles_txt_mv	Zhang, Xingyu @@aut@@ Zhang, Xiongwei @@aut@@ Liu, Wei @@aut@@ Zou, Xia @@aut@@ Sun, Meng @@aut@@ Zhao, Jian @@aut@@
publishDateDaySort_date	2022-01-01T00:00:00Z
hierarchy_top_id	308447832
dewey-sort	14
id	ELV008696357
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV008696357</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230524152201.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230509s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.engappai.2022.105469</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV008696357</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0952-1976(22)00459-6</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">50.23</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.72</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhang, Xingyu</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-0783-684X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Automatic speaker verification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Spoofing countermeasures</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Adversarial example</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Joint attack</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Waveform gradients</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Xiongwei</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Wei</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zou, Xia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sun, Meng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhao, Jian</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-3508-756X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Engineering applications of artificial intelligence</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1988</subfield><subfield code="g">116</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)308447832</subfield><subfield code="w">(DE-600)1502275-4</subfield><subfield code="w">(DE-576)094752524</subfield><subfield code="x">0952-1976</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:116</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2008</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2010</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2038</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2065</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2088</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2113</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2470</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4046</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">50.23</subfield><subfield code="j">Regelungstechnik</subfield><subfield code="j">Steuerungstechnik</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.72</subfield><subfield code="j">Künstliche Intelligenz</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">116</subfield></datafield></record></collection>
author	Zhang, Xingyu
spellingShingle	Zhang, Xingyu ddc 004 bkl 50.23 bkl 54.72 misc Automatic speaker verification misc Spoofing countermeasures misc Adversarial example misc Joint attack misc Waveform gradients Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures
authorStr	Zhang, Xingyu
ppnlink_with_tag_str_mv	@@773@@(DE-627)308447832
format	electronic Article
dewey-ones	004 - Data processing & computer science
delete_txt_mv	keep
author_role	aut aut aut aut aut aut
collection	elsevier
remote_str	true
illustrated	Not Illustrated
issn	0952-1976
topic_title	004 DE-600 50.23 bkl 54.72 bkl Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures Automatic speaker verification Spoofing countermeasures Adversarial example Joint attack Waveform gradients
topic	ddc 004 bkl 50.23 bkl 54.72 misc Automatic speaker verification misc Spoofing countermeasures misc Adversarial example misc Joint attack misc Waveform gradients
topic_unstemmed	ddc 004 bkl 50.23 bkl 54.72 misc Automatic speaker verification misc Spoofing countermeasures misc Adversarial example misc Joint attack misc Waveform gradients
topic_browse	ddc 004 bkl 50.23 bkl 54.72 misc Automatic speaker verification misc Spoofing countermeasures misc Adversarial example misc Joint attack misc Waveform gradients
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Engineering applications of artificial intelligence
hierarchy_parent_id	308447832
dewey-tens	000 - Computer science, knowledge & systems
hierarchy_top_title	Engineering applications of artificial intelligence
isfreeaccess_txt	false
familylinks_str_mv	(DE-627)308447832 (DE-600)1502275-4 (DE-576)094752524
title	Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures
ctrlnum	(DE-627)ELV008696357 (ELSEVIER)S0952-1976(22)00459-6
title_full	Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures
author_sort	Zhang, Xingyu
journal	Engineering applications of artificial intelligence
journalStr	Engineering applications of artificial intelligence
lang_code	eng
isOA_bool	false
dewey-hundreds	000 - Computer science, information & general works
recordtype	marc
publishDateSort	2022
contenttype_str_mv	zzz
author_browse	Zhang, Xingyu Zhang, Xiongwei Liu, Wei Zou, Xia Sun, Meng Zhao, Jian
container_volume	116
class	004 DE-600 50.23 bkl 54.72 bkl
format_se	Elektronische Aufsätze
author-letter	Zhang, Xingyu
doi_str_mv	10.1016/j.engappai.2022.105469
normlink	(ORCID)0000-0003-0783-684X (ORCID)0000-0002-3508-756X
normlink_prefix_str_mv	(orcid)0000-0003-0783-684X (orcid)0000-0002-3508-756X
dewey-full	004
author2-role	verfasserin
title_sort	waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures
title_auth	Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures
abstract	Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated.
abstractGer	Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated.
abstract_unstemmed	Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated.
collection_details	GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393
title_short	Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures
remote_bool	true
author2	Zhang, Xiongwei Liu, Wei Zou, Xia Sun, Meng Zhao, Jian
author2Str	Zhang, Xiongwei Liu, Wei Zou, Xia Sun, Meng Zhao, Jian
ppnlink	308447832
mediatype_str_mv	c
isOA_txt	false
hochschulschrift_bool	false
doi_str	10.1016/j.engappai.2022.105469
up_date	2024-07-06T20:35:24.887Z
_version_	1803863326604656640
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV008696357</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230524152201.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230509s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.engappai.2022.105469</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV008696357</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0952-1976(22)00459-6</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">50.23</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.72</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhang, Xingyu</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-0783-684X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV systems usually work together with spoofing countermeasures (CM) to exclude fake voices generated by text-to-speech (TTS) or voice conversion (VC). The deployment of CM would reduce the capability of the adversarial samples on deceiving ASV. Although additional perturbations against CM may be generated and put on the crafted adversarial examples against ASV to yield new adversarial examples against both ASV and CM, those additional perturbations would however hinder the examples’ adversarial effectiveness on ASV. In this paper, a novel joint approach is proposed to generate adversarial examples by considering attacking ASV and CM simultaneously. For any voice from TTS, VC or a real-world speaker, our crafted adversarial perturbations will turn its original labels on CM and speaker ID to bonafide and some target speaker ID, correspondingly. In our approach, a differentiable front-end is introduced to replace the conventional hand-crafted time–frequency feature extractor. Perturbations can thus be estimated by updating the gradients of the joint objective of ASV and CM on the waveform variables. The proposed method has demonstrated a 99.3% success rate on white-box logical access attacks to deceive ASV and CM simultaneously, which outperforms the baselines of 65.3% and 36.7%. Furthermore, transferability on black-box and physical settings has also been validated.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Automatic speaker verification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Spoofing countermeasures</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Adversarial example</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Joint attack</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Waveform gradients</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Xiongwei</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Wei</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zou, Xia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sun, Meng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhao, Jian</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-3508-756X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Engineering applications of artificial intelligence</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1988</subfield><subfield code="g">116</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)308447832</subfield><subfield code="w">(DE-600)1502275-4</subfield><subfield code="w">(DE-576)094752524</subfield><subfield code="x">0952-1976</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:116</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2008</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2010</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2038</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2065</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2088</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2113</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2470</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4046</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">50.23</subfield><subfield code="j">Regelungstechnik</subfield><subfield code="j">Steuerungstechnik</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.72</subfield><subfield code="j">Künstliche Intelligenz</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">116</subfield></datafield></record></collection>
score	7.399617

Nicht das Richtige dabei?

Schreiben Sie uns!

Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?