Gray-box Adversarial Testing for Control Systems with Machine Learning Component

Neural Networks (NN) have been proposed in the past as an effective means for both modeling and control of systems with very complex dynamics. However, despite the extensive research, NN-based controllers have not been adopted by the industry for safety critical systems. The primary reason is that s...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-12
Main Authors: Yaghoubi, Shakiba, Fainekos, Georgios
Format: Article
Language:English
Subjects:
Computer simulation
Control systems
Controllers
Machine learning
Neural networks
Safety critical
Simulated annealing
System effectiveness
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Yaghoubi, Shakiba
Fainekos, Georgios
description Neural Networks (NN) have been proposed in the past as an effective means for both modeling and control of systems with very complex dynamics. However, despite the extensive research, NN-based controllers have not been adopted by the industry for safety critical systems. The primary reason is that systems with learning based controllers are notoriously hard to test and verify. Even harder is the analysis of such systems against system-level specifications. In this paper, we provide a gradient based method for searching the input space of a closed-loop control system in order to find adversarial samples against some system-level requirements. Our experimental results show that combined with randomized search, our method outperforms Simulated Annealing optimization.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2162263652</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2162263652</sourcerecordid><originalsourceid>FETCH-proquest_journals_21622636523</originalsourceid><addsrcrecordid>eNqNjMsKgkAUQIcgSMp_GGgt6J2c2ob0WBQEuZepxlR0rt0ZK_8-gz6g1VmcwxkxD4SIgtUCYMJ8a6swDEEuIY6Fx047Un1wwTdf356arKJS1TzV1pXmznMknqBxhDU_99bpxvJX6Qp-VNeiNJoftCLzLRNsWjTauBkb56q22v9xyubbTZrsg5bw0Q3frMKOzKAyiCSAFDIG8V_1AWclPwQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2162263652</pqid></control><display><type>article</type><title>Gray-box Adversarial Testing for Control Systems with Machine Learning Component</title><source>Publicly Available Content Database</source><creator>Yaghoubi, Shakiba ; Fainekos, Georgios</creator><creatorcontrib>Yaghoubi, Shakiba ; Fainekos, Georgios</creatorcontrib><description>Neural Networks (NN) have been proposed in the past as an effective means for both modeling and control of systems with very complex dynamics. However, despite the extensive research, NN-based controllers have not been adopted by the industry for safety critical systems. The primary reason is that systems with learning based controllers are notoriously hard to test and verify. Even harder is the analysis of such systems against system-level specifications. In this paper, we provide a gradient based method for searching the input space of a closed-loop control system in order to find adversarial samples against some system-level requirements. Our experimental results show that combined with randomized search, our method outperforms Simulated Annealing optimization.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer simulation ; Control systems ; Controllers ; Machine learning ; Neural networks ; Safety critical ; Simulated annealing ; System effectiveness</subject><ispartof>arXiv.org, 2018-12</ispartof><rights>2018. 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>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2162263652?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25732,36991,44569</link.rule.ids></links><search><creatorcontrib>Yaghoubi, Shakiba</creatorcontrib><creatorcontrib>Fainekos, Georgios</creatorcontrib><title>Gray-box Adversarial Testing for Control Systems with Machine Learning Component</title><title>arXiv.org</title><description>Neural Networks (NN) have been proposed in the past as an effective means for both modeling and control of systems with very complex dynamics. However, despite the extensive research, NN-based controllers have not been adopted by the industry for safety critical systems. The primary reason is that systems with learning based controllers are notoriously hard to test and verify. Even harder is the analysis of such systems against system-level specifications. In this paper, we provide a gradient based method for searching the input space of a closed-loop control system in order to find adversarial samples against some system-level requirements. Our experimental results show that combined with randomized search, our method outperforms Simulated Annealing optimization.</description><subject>Computer simulation</subject><subject>Control systems</subject><subject>Controllers</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Safety critical</subject><subject>Simulated annealing</subject><subject>System effectiveness</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjMsKgkAUQIcgSMp_GGgt6J2c2ob0WBQEuZepxlR0rt0ZK_8-gz6g1VmcwxkxD4SIgtUCYMJ8a6swDEEuIY6Fx047Un1wwTdf356arKJS1TzV1pXmznMknqBxhDU_99bpxvJX6Qp-VNeiNJoftCLzLRNsWjTauBkb56q22v9xyubbTZrsg5bw0Q3frMKOzKAyiCSAFDIG8V_1AWclPwQ</recordid><startdate>20181231</startdate><enddate>20181231</enddate><creator>Yaghoubi, Shakiba</creator><creator>Fainekos, Georgios</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>20181231</creationdate><title>Gray-box Adversarial Testing for Control Systems with Machine Learning Component</title><author>Yaghoubi, Shakiba ; Fainekos, Georgios</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_21622636523</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer simulation</topic><topic>Control systems</topic><topic>Controllers</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Safety critical</topic><topic>Simulated annealing</topic><topic>System effectiveness</topic><toplevel>online_resources</toplevel><creatorcontrib>Yaghoubi, Shakiba</creatorcontrib><creatorcontrib>Fainekos, Georgios</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Databases</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest 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>Yaghoubi, Shakiba</au><au>Fainekos, Georgios</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Gray-box Adversarial Testing for Control Systems with Machine Learning Component</atitle><jtitle>arXiv.org</jtitle><date>2018-12-31</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Neural Networks (NN) have been proposed in the past as an effective means for both modeling and control of systems with very complex dynamics. However, despite the extensive research, NN-based controllers have not been adopted by the industry for safety critical systems. The primary reason is that systems with learning based controllers are notoriously hard to test and verify. Even harder is the analysis of such systems against system-level specifications. In this paper, we provide a gradient based method for searching the input space of a closed-loop control system in order to find adversarial samples against some system-level requirements. Our experimental results show that combined with randomized search, our method outperforms Simulated Annealing optimization.</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, 2018-12
issn 2331-8422
language eng
recordid cdi_proquest_journals_2162263652
source Publicly Available Content Database
subjects Computer simulation
Control systems
Controllers
Machine learning
Neural networks
Safety critical
Simulated annealing
System effectiveness
title Gray-box Adversarial Testing for Control Systems with Machine Learning Component
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T00%3A49%3A37IST&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=Gray-box%20Adversarial%20Testing%20for%20Control%20Systems%20with%20Machine%20Learning%20Component&rft.jtitle=arXiv.org&rft.au=Yaghoubi,%20Shakiba&rft.date=2018-12-31&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2162263652%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_21622636523%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2162263652&rft_id=info:pmid/&rfr_iscdi=true