Multi-layer perceptron for network intrusion detection
Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Rosay, Arnaud [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© Institut Mines-Télécom and Springer Nature Switzerland AG 2021 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Annals of telecommunications - Springer International Publishing, 1946, 77(2021), 5-6 vom: 28. Mai, Seite 371-394 |
|---|---|
| Übergeordnetes Werk: |
volume:77 ; year:2021 ; number:5-6 ; day:28 ; month:05 ; pages:371-394 |
| Links: |
|---|
| DOI / URN: |
10.1007/s12243-021-00852-0 |
|---|
| Katalog-ID: |
OLC2078896497 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2078896497 | ||
| 003 | DE-627 | ||
| 005 | 20230506031119.0 | ||
| 007 | tu | ||
| 008 | 221220s2021 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s12243-021-00852-0 |2 doi | |
| 035 | |a (DE-627)OLC2078896497 | ||
| 035 | |a (DE-He213)s12243-021-00852-0-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 620 |q VZ |
| 100 | 1 | |a Rosay, Arnaud |e verfasserin |0 (orcid)0000-0001-5937-5331 |4 aut | |
| 245 | 1 | 0 | |a Multi-layer perceptron for network intrusion detection |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 | ||
| 520 | |a Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. | ||
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Multi-layer perceptron | |
| 650 | 4 | |a Network intrusion detection | |
| 650 | 4 | |a CIC-IDS2017 data set | |
| 650 | 4 | |a CSE-CIC-IDS2018 data set | |
| 700 | 1 | |a Riou, Kévin |0 (orcid)0000-0002-0747-3324 |4 aut | |
| 700 | 1 | |a Carlier, Florent |0 (orcid)0000-0003-0314-3667 |4 aut | |
| 700 | 1 | |a Leroux, Pascal |0 (orcid)0000-0002-4447-7244 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Annals of telecommunications |d Springer International Publishing, 1946 |g 77(2021), 5-6 vom: 28. Mai, Seite 371-394 |w (DE-627)129514497 |w (DE-600)210938-4 |w (DE-576)014923726 |x 0003-4347 |7 nnns |
| 773 | 1 | 8 | |g volume:77 |g year:2021 |g number:5-6 |g day:28 |g month:05 |g pages:371-394 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s12243-021-00852-0 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-TEC | ||
| 912 | |a SSG-OLC-MKW | ||
| 951 | |a AR | ||
| 952 | |d 77 |j 2021 |e 5-6 |b 28 |c 05 |h 371-394 | ||
| author_variant |
a r ar k r kr f c fc p l pl |
|---|---|
| matchkey_str |
article:00034347:2021----::utlyrecprnontoknrs |
| hierarchy_sort_str |
2021 |
| publishDate |
2021 |
| allfields |
10.1007/s12243-021-00852-0 doi (DE-627)OLC2078896497 (DE-He213)s12243-021-00852-0-p DE-627 ger DE-627 rakwb eng 620 VZ Rosay, Arnaud verfasserin (orcid)0000-0001-5937-5331 aut Multi-layer perceptron for network intrusion detection 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. Machine learning Multi-layer perceptron Network intrusion detection CIC-IDS2017 data set CSE-CIC-IDS2018 data set Riou, Kévin (orcid)0000-0002-0747-3324 aut Carlier, Florent (orcid)0000-0003-0314-3667 aut Leroux, Pascal (orcid)0000-0002-4447-7244 aut Enthalten in Annals of telecommunications Springer International Publishing, 1946 77(2021), 5-6 vom: 28. Mai, Seite 371-394 (DE-627)129514497 (DE-600)210938-4 (DE-576)014923726 0003-4347 nnns volume:77 year:2021 number:5-6 day:28 month:05 pages:371-394 https://doi.org/10.1007/s12243-021-00852-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MKW AR 77 2021 5-6 28 05 371-394 |
| spelling |
10.1007/s12243-021-00852-0 doi (DE-627)OLC2078896497 (DE-He213)s12243-021-00852-0-p DE-627 ger DE-627 rakwb eng 620 VZ Rosay, Arnaud verfasserin (orcid)0000-0001-5937-5331 aut Multi-layer perceptron for network intrusion detection 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. Machine learning Multi-layer perceptron Network intrusion detection CIC-IDS2017 data set CSE-CIC-IDS2018 data set Riou, Kévin (orcid)0000-0002-0747-3324 aut Carlier, Florent (orcid)0000-0003-0314-3667 aut Leroux, Pascal (orcid)0000-0002-4447-7244 aut Enthalten in Annals of telecommunications Springer International Publishing, 1946 77(2021), 5-6 vom: 28. Mai, Seite 371-394 (DE-627)129514497 (DE-600)210938-4 (DE-576)014923726 0003-4347 nnns volume:77 year:2021 number:5-6 day:28 month:05 pages:371-394 https://doi.org/10.1007/s12243-021-00852-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MKW AR 77 2021 5-6 28 05 371-394 |
| allfields_unstemmed |
10.1007/s12243-021-00852-0 doi (DE-627)OLC2078896497 (DE-He213)s12243-021-00852-0-p DE-627 ger DE-627 rakwb eng 620 VZ Rosay, Arnaud verfasserin (orcid)0000-0001-5937-5331 aut Multi-layer perceptron for network intrusion detection 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. Machine learning Multi-layer perceptron Network intrusion detection CIC-IDS2017 data set CSE-CIC-IDS2018 data set Riou, Kévin (orcid)0000-0002-0747-3324 aut Carlier, Florent (orcid)0000-0003-0314-3667 aut Leroux, Pascal (orcid)0000-0002-4447-7244 aut Enthalten in Annals of telecommunications Springer International Publishing, 1946 77(2021), 5-6 vom: 28. Mai, Seite 371-394 (DE-627)129514497 (DE-600)210938-4 (DE-576)014923726 0003-4347 nnns volume:77 year:2021 number:5-6 day:28 month:05 pages:371-394 https://doi.org/10.1007/s12243-021-00852-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MKW AR 77 2021 5-6 28 05 371-394 |
| allfieldsGer |
10.1007/s12243-021-00852-0 doi (DE-627)OLC2078896497 (DE-He213)s12243-021-00852-0-p DE-627 ger DE-627 rakwb eng 620 VZ Rosay, Arnaud verfasserin (orcid)0000-0001-5937-5331 aut Multi-layer perceptron for network intrusion detection 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. Machine learning Multi-layer perceptron Network intrusion detection CIC-IDS2017 data set CSE-CIC-IDS2018 data set Riou, Kévin (orcid)0000-0002-0747-3324 aut Carlier, Florent (orcid)0000-0003-0314-3667 aut Leroux, Pascal (orcid)0000-0002-4447-7244 aut Enthalten in Annals of telecommunications Springer International Publishing, 1946 77(2021), 5-6 vom: 28. Mai, Seite 371-394 (DE-627)129514497 (DE-600)210938-4 (DE-576)014923726 0003-4347 nnns volume:77 year:2021 number:5-6 day:28 month:05 pages:371-394 https://doi.org/10.1007/s12243-021-00852-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MKW AR 77 2021 5-6 28 05 371-394 |
| allfieldsSound |
10.1007/s12243-021-00852-0 doi (DE-627)OLC2078896497 (DE-He213)s12243-021-00852-0-p DE-627 ger DE-627 rakwb eng 620 VZ Rosay, Arnaud verfasserin (orcid)0000-0001-5937-5331 aut Multi-layer perceptron for network intrusion detection 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. Machine learning Multi-layer perceptron Network intrusion detection CIC-IDS2017 data set CSE-CIC-IDS2018 data set Riou, Kévin (orcid)0000-0002-0747-3324 aut Carlier, Florent (orcid)0000-0003-0314-3667 aut Leroux, Pascal (orcid)0000-0002-4447-7244 aut Enthalten in Annals of telecommunications Springer International Publishing, 1946 77(2021), 5-6 vom: 28. Mai, Seite 371-394 (DE-627)129514497 (DE-600)210938-4 (DE-576)014923726 0003-4347 nnns volume:77 year:2021 number:5-6 day:28 month:05 pages:371-394 https://doi.org/10.1007/s12243-021-00852-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MKW AR 77 2021 5-6 28 05 371-394 |
| language |
English |
| source |
Enthalten in Annals of telecommunications 77(2021), 5-6 vom: 28. Mai, Seite 371-394 volume:77 year:2021 number:5-6 day:28 month:05 pages:371-394 |
| sourceStr |
Enthalten in Annals of telecommunications 77(2021), 5-6 vom: 28. Mai, Seite 371-394 volume:77 year:2021 number:5-6 day:28 month:05 pages:371-394 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Machine learning Multi-layer perceptron Network intrusion detection CIC-IDS2017 data set CSE-CIC-IDS2018 data set |
| dewey-raw |
620 |
| isfreeaccess_bool |
false |
| container_title |
Annals of telecommunications |
| authorswithroles_txt_mv |
Rosay, Arnaud @@aut@@ Riou, Kévin @@aut@@ Carlier, Florent @@aut@@ Leroux, Pascal @@aut@@ |
| publishDateDaySort_date |
2021-05-28T00:00:00Z |
| hierarchy_top_id |
129514497 |
| dewey-sort |
3620 |
| id |
OLC2078896497 |
| 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">OLC2078896497</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506031119.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s12243-021-00852-0</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2078896497</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s12243-021-00852-0-p</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">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">620</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Rosay, Arnaud</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-5937-5331</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Multi-layer perceptron for network intrusion detection</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Institut Mines-Télécom and Springer Nature Switzerland AG 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-layer perceptron</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Network intrusion detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">CIC-IDS2017 data set</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">CSE-CIC-IDS2018 data set</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Riou, Kévin</subfield><subfield code="0">(orcid)0000-0002-0747-3324</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Carlier, Florent</subfield><subfield code="0">(orcid)0000-0003-0314-3667</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Leroux, Pascal</subfield><subfield code="0">(orcid)0000-0002-4447-7244</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Annals of telecommunications</subfield><subfield code="d">Springer International Publishing, 1946</subfield><subfield code="g">77(2021), 5-6 vom: 28. Mai, Seite 371-394</subfield><subfield code="w">(DE-627)129514497</subfield><subfield code="w">(DE-600)210938-4</subfield><subfield code="w">(DE-576)014923726</subfield><subfield code="x">0003-4347</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:77</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:5-6</subfield><subfield code="g">day:28</subfield><subfield code="g">month:05</subfield><subfield code="g">pages:371-394</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s12243-021-00852-0</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MKW</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">77</subfield><subfield code="j">2021</subfield><subfield code="e">5-6</subfield><subfield code="b">28</subfield><subfield code="c">05</subfield><subfield code="h">371-394</subfield></datafield></record></collection>
|
| author |
Rosay, Arnaud |
| spellingShingle |
Rosay, Arnaud ddc 620 misc Machine learning misc Multi-layer perceptron misc Network intrusion detection misc CIC-IDS2017 data set misc CSE-CIC-IDS2018 data set Multi-layer perceptron for network intrusion detection |
| authorStr |
Rosay, Arnaud |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)129514497 |
| format |
Article |
| dewey-ones |
620 - Engineering & allied operations |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0003-4347 |
| topic_title |
620 VZ Multi-layer perceptron for network intrusion detection Machine learning Multi-layer perceptron Network intrusion detection CIC-IDS2017 data set CSE-CIC-IDS2018 data set |
| topic |
ddc 620 misc Machine learning misc Multi-layer perceptron misc Network intrusion detection misc CIC-IDS2017 data set misc CSE-CIC-IDS2018 data set |
| topic_unstemmed |
ddc 620 misc Machine learning misc Multi-layer perceptron misc Network intrusion detection misc CIC-IDS2017 data set misc CSE-CIC-IDS2018 data set |
| topic_browse |
ddc 620 misc Machine learning misc Multi-layer perceptron misc Network intrusion detection misc CIC-IDS2017 data set misc CSE-CIC-IDS2018 data set |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Annals of telecommunications |
| hierarchy_parent_id |
129514497 |
| dewey-tens |
620 - Engineering |
| hierarchy_top_title |
Annals of telecommunications |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)129514497 (DE-600)210938-4 (DE-576)014923726 |
| title |
Multi-layer perceptron for network intrusion detection |
| ctrlnum |
(DE-627)OLC2078896497 (DE-He213)s12243-021-00852-0-p |
| title_full |
Multi-layer perceptron for network intrusion detection |
| author_sort |
Rosay, Arnaud |
| journal |
Annals of telecommunications |
| journalStr |
Annals of telecommunications |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
txt |
| container_start_page |
371 |
| author_browse |
Rosay, Arnaud Riou, Kévin Carlier, Florent Leroux, Pascal |
| container_volume |
77 |
| class |
620 VZ |
| format_se |
Aufsätze |
| author-letter |
Rosay, Arnaud |
| doi_str_mv |
10.1007/s12243-021-00852-0 |
| normlink |
(ORCID)0000-0001-5937-5331 (ORCID)0000-0002-0747-3324 (ORCID)0000-0003-0314-3667 (ORCID)0000-0002-4447-7244 |
| normlink_prefix_str_mv |
(orcid)0000-0001-5937-5331 (orcid)0000-0002-0747-3324 (orcid)0000-0003-0314-3667 (orcid)0000-0002-4447-7244 |
| dewey-full |
620 |
| title_sort |
multi-layer perceptron for network intrusion detection |
| title_auth |
Multi-layer perceptron for network intrusion detection |
| abstract |
Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 |
| abstractGer |
Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 |
| abstract_unstemmed |
Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets. © Institut Mines-Télécom and Springer Nature Switzerland AG 2021 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MKW |
| container_issue |
5-6 |
| title_short |
Multi-layer perceptron for network intrusion detection |
| url |
https://doi.org/10.1007/s12243-021-00852-0 |
| remote_bool |
false |
| author2 |
Riou, Kévin Carlier, Florent Leroux, Pascal |
| author2Str |
Riou, Kévin Carlier, Florent Leroux, Pascal |
| ppnlink |
129514497 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s12243-021-00852-0 |
| up_date |
2024-07-03T22:38:04.484Z |
| _version_ |
1803599252799094785 |
| 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">OLC2078896497</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506031119.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s12243-021-00852-0</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2078896497</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s12243-021-00852-0-p</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">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">620</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Rosay, Arnaud</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-5937-5331</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Multi-layer perceptron for network intrusion detection</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Institut Mines-Télécom and Springer Nature Switzerland AG 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract The Internet connection is becoming ubiquitous in embedded systems, making them potential victims of intrusion. Although gaining popularity in recent years, deep learning based intrusion detection systems tend to produce worse results than those using traditional machine learning algorithms. On the contrary, we propose an end-to-end methodology allowing a neural network to outperform traditional machine learning algorithms. We demonstrate high performance score on CIC-IDS2017 data set, showing an accuracy greater than 99% and a false positive rate lower than 0.5%. Our results are compared to traditional machine learning algorithms and previous studies. Then, we show that our approach can be successfully applied to CSE-CIC-IDS2018 data set, confirming that neural network can reach better scores than other machine learning algorithms. Our performance is compared to previous work on this data set. We further deployed our solution on a system-on-chip for automotive, allowing to characterize real-time performance aspect on an embedded system, both for feature extraction and inference. Finally, a discussion opens up on problems related to some attacks that are particularly difficult to detect with flow-based techniques and weaknesses found in the data sets.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-layer perceptron</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Network intrusion detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">CIC-IDS2017 data set</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">CSE-CIC-IDS2018 data set</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Riou, Kévin</subfield><subfield code="0">(orcid)0000-0002-0747-3324</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Carlier, Florent</subfield><subfield code="0">(orcid)0000-0003-0314-3667</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Leroux, Pascal</subfield><subfield code="0">(orcid)0000-0002-4447-7244</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Annals of telecommunications</subfield><subfield code="d">Springer International Publishing, 1946</subfield><subfield code="g">77(2021), 5-6 vom: 28. Mai, Seite 371-394</subfield><subfield code="w">(DE-627)129514497</subfield><subfield code="w">(DE-600)210938-4</subfield><subfield code="w">(DE-576)014923726</subfield><subfield code="x">0003-4347</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:77</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:5-6</subfield><subfield code="g">day:28</subfield><subfield code="g">month:05</subfield><subfield code="g">pages:371-394</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s12243-021-00852-0</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MKW</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">77</subfield><subfield code="j">2021</subfield><subfield code="e">5-6</subfield><subfield code="b">28</subfield><subfield code="c">05</subfield><subfield code="h">371-394</subfield></datafield></record></collection>
|
| score |
7.4009867 |