Show simple item record

dc.contributor.authorKiourti, Panagiotaen_US
dc.contributor.authorWardega, Kacperen_US
dc.contributor.authorJha, Susmiten_US
dc.contributor.authorLi, Wenchaoen_US
dc.date2020-02-27
dc.date.accessioned2020-12-21T19:35:40Z
dc.date.available2020-12-21T19:35:40Z
dc.date.issued2020
dc.identifier.citationPanagiota Kiourti, Kacper Wardega, Susmit Jha, Wenchao Li. "TrojDRL: Evaluation of Backdoor Attacks on Deep Reinforcement Learning." 57th ACM/EDAC/IEEE Design Automation Conference,
dc.identifier.urihttps://hdl.handle.net/2144/41836
dc.description.abstractWe present TrojDRL, a tool for exploring and evaluating backdoor attacks on deep reinforcement learning agents. TrojDRL exploits the sequential nature of deep reinforcement learning (DRL) and considers different gradations of threat models. We show that untargeted attacks on state-of-the-art actor-critic algorithms can circumvent existing defenses built on the assumption of backdoors being targeted. We evaluated TrojDRL on a broad set of DRL benchmarks and showed that the attacks require only poisoning as little as 0.025% of training data. Compared with existing works of backdoor attacks on classification models, TrojDRL provides a first step towards understanding the vulnerability of DRL agents.en_US
dc.language.isoen_US
dc.relation.ispartof57th ACM/EDAC/IEEE Design Automation Conference
dc.rights© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_US
dc.subjectLearning (artificial intelligence)en_US
dc.subjectMulti-agent systemsen_US
dc.subjectNeural netsen_US
dc.subjectSecurity of dataen_US
dc.subjectMachine learningen_US
dc.subjectReliability and robustnessen_US
dc.titleTrojDRL: evaluation of backdoor attacks on deep reinforcement learningen_US
dc.typeArticleen_US
dc.description.versionAccepted manuscripten_US
dc.identifier.doi10.1109/DAC18072.2020.9218663
pubs.declined2020-03-02T02:14:44.946+0000en_US
pubs.elements-sourcemanual-entryen_US
pubs.notesEmbargo: Not knownen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Engineeringen_US
pubs.organisational-groupBoston University, College of Engineering, Department of Electrical & Computer Engineeringen_US
pubs.publication-statusAccepteden_US
dc.identifier.orcid0000-0003-0153-4648 (Li, Wenchao)
dc.identifier.mycv550117


This item appears in the following Collection(s)

Show simple item record