Robustness of ML-Enhanced IDS to Stealthy Adversaries

Intrusion Detection Systems (IDS) enhanced with Machine Learning (ML) have demonstrated the capacity to efficiently build a prototype of "normal" cyber behaviors in order to detect cyber threats' activity with greater accuracy than traditional rule-based IDS. Because these are largely...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-04
Hauptverfasser: Wong, Vance, Emanuello, John
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Wong, Vance
Emanuello, John
description Intrusion Detection Systems (IDS) enhanced with Machine Learning (ML) have demonstrated the capacity to efficiently build a prototype of "normal" cyber behaviors in order to detect cyber threats' activity with greater accuracy than traditional rule-based IDS. Because these are largely black boxes, their acceptance requires proof of robustness to stealthy adversaries. Since it is impossible to build a baseline from activity completely clean of that of malicious cyber actors (outside of controlled experiments), the training data for deployed models will be poisoned with examples of activity that analysts would want to be alerted about. We train an autoencoder-based anomaly detection system on network activity with various proportions of malicious activity mixed in and demonstrate that they are robust to this sort of poisoning.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2517117005</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2517117005</sourcerecordid><originalsourceid>FETCH-proquest_journals_25171170053</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwDcpPKi0uyUstLlbIT1Pw9dF1zctIzEtOTVHwdAlWKMlXCC5JTcwpyahUcEwpSy0qTizKTC3mYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4I1NDc0NDcwMDU2PiVAEANKc0Jw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2517117005</pqid></control><display><type>article</type><title>Robustness of ML-Enhanced IDS to Stealthy Adversaries</title><source>Free E- Journals</source><creator>Wong, Vance ; Emanuello, John</creator><creatorcontrib>Wong, Vance ; Emanuello, John</creatorcontrib><description>Intrusion Detection Systems (IDS) enhanced with Machine Learning (ML) have demonstrated the capacity to efficiently build a prototype of "normal" cyber behaviors in order to detect cyber threats' activity with greater accuracy than traditional rule-based IDS. Because these are largely black boxes, their acceptance requires proof of robustness to stealthy adversaries. Since it is impossible to build a baseline from activity completely clean of that of malicious cyber actors (outside of controlled experiments), the training data for deployed models will be poisoned with examples of activity that analysts would want to be alerted about. We train an autoencoder-based anomaly detection system on network activity with various proportions of malicious activity mixed in and demonstrate that they are robust to this sort of poisoning.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Anomalies ; Cybersecurity ; Machine learning ; Robustness ; Security management</subject><ispartof>arXiv.org, 2021-04</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Wong, Vance</creatorcontrib><creatorcontrib>Emanuello, John</creatorcontrib><title>Robustness of ML-Enhanced IDS to Stealthy Adversaries</title><title>arXiv.org</title><description>Intrusion Detection Systems (IDS) enhanced with Machine Learning (ML) have demonstrated the capacity to efficiently build a prototype of "normal" cyber behaviors in order to detect cyber threats' activity with greater accuracy than traditional rule-based IDS. Because these are largely black boxes, their acceptance requires proof of robustness to stealthy adversaries. Since it is impossible to build a baseline from activity completely clean of that of malicious cyber actors (outside of controlled experiments), the training data for deployed models will be poisoned with examples of activity that analysts would want to be alerted about. We train an autoencoder-based anomaly detection system on network activity with various proportions of malicious activity mixed in and demonstrate that they are robust to this sort of poisoning.</description><subject>Anomalies</subject><subject>Cybersecurity</subject><subject>Machine learning</subject><subject>Robustness</subject><subject>Security management</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwDcpPKi0uyUstLlbIT1Pw9dF1zctIzEtOTVHwdAlWKMlXCC5JTcwpyahUcEwpSy0qTizKTC3mYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4I1NDc0NDcwMDU2PiVAEANKc0Jw</recordid><startdate>20210421</startdate><enddate>20210421</enddate><creator>Wong, Vance</creator><creator>Emanuello, John</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210421</creationdate><title>Robustness of ML-Enhanced IDS to Stealthy Adversaries</title><author>Wong, Vance ; Emanuello, John</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25171170053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Anomalies</topic><topic>Cybersecurity</topic><topic>Machine learning</topic><topic>Robustness</topic><topic>Security management</topic><toplevel>online_resources</toplevel><creatorcontrib>Wong, Vance</creatorcontrib><creatorcontrib>Emanuello, John</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wong, Vance</au><au>Emanuello, John</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Robustness of ML-Enhanced IDS to Stealthy Adversaries</atitle><jtitle>arXiv.org</jtitle><date>2021-04-21</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>Intrusion Detection Systems (IDS) enhanced with Machine Learning (ML) have demonstrated the capacity to efficiently build a prototype of "normal" cyber behaviors in order to detect cyber threats' activity with greater accuracy than traditional rule-based IDS. Because these are largely black boxes, their acceptance requires proof of robustness to stealthy adversaries. Since it is impossible to build a baseline from activity completely clean of that of malicious cyber actors (outside of controlled experiments), the training data for deployed models will be poisoned with examples of activity that analysts would want to be alerted about. We train an autoencoder-based anomaly detection system on network activity with various proportions of malicious activity mixed in and demonstrate that they are robust to this sort of poisoning.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-04
issn 2331-8422
language eng
recordid cdi_proquest_journals_2517117005
source Free E- Journals
subjects Anomalies
Cybersecurity
Machine learning
Robustness
Security management
title Robustness of ML-Enhanced IDS to Stealthy Adversaries
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T03%3A06%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Robustness%20of%20ML-Enhanced%20IDS%20to%20Stealthy%20Adversaries&rft.jtitle=arXiv.org&rft.au=Wong,%20Vance&rft.date=2021-04-21&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2517117005%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2517117005&rft_id=info:pmid/&rfr_iscdi=true