Attacking Reinforcement Learning Agents via Data Poisoning and How to Defend
Attacking Reinforcement Learning Agents via Data Poisoning and How to Defend
Bandit algorithms and Reinforcement Learning models have been widely used in many successful applications in the recent years. However, it has been shown that these algorithms are vulnerable against data poisoning attacks, where an Adversary can manipulate the feedback of our Agent, guiding it to learn a suboptimal (or a targeted) behaviour on the long run. In this talk I will discuss the theoretical boundaries of such attacks, such as what the provable necessary and sufficient conditions are for a successful attack against different types of learning agents. I will also discuss a verification based way of defence mechanism against such data poisoning attacks. This talk is a summary of our recent papers published a AAAI 2022, IJCAI 2022, and AAMAS 2024.
Click the link below to join the seminar at the following time
Melbourne (AEST) : 6 May 2024 11:00 AM
Japan (JST) : 6 May 2024 10:00 AM
China (CST) : 6 May 2024 9:00 AM
India (IST) : 6 May 2024 6:30 AM
Central Europe (CEST) : 6 May 2024 3:00 AM
New York (EDT) : 5 May 2024 9:00 PM
Los Angeles (PDT) : 5 May 2024 6:00 PM
Join seminar
Webinar passcode: 055806 (if asked when joining the seminar)
About the speaker
Associate Professor, University of Warwick
Long is currently the Deputy-Head and the Director of Research at the department of Computer Science, University of Warwick, UK. He is also the university’s Chair of Digital Research Spotlight. Long has been doing active research in a number of key areas of Artificial Intelligence and multi-agent systems, mainly focusing on multi-armed bandits, game theory, and incentive engineering, and their applications to AI for Social Good. He has published more than 80 papers at peer-reviewed A* conferences in AI/ML (including AAAI, AAMAS, CVPR, ECAI, IJCAI, NeurIPS, UAI) and journals (JAAMAS, AIJ), and have received a number of prestigious national/international awards, including 2 best paper honourable mention awards at top-tier AI conferences (AAAI, ECAI), 2 Best PhD Thesis Awards (one in the UK and one in Europe), and the co-recipient of the 2021 AIJ Prominent Paper Award (for one of the 2 most influential papers between 2014-2021 published at the Artificial Intelligence Journal).
Monash University values the privacy of every individual's personal information and is committed to the protection of that information from unauthorised use and disclosure except where permitted by law. For information about the handling of your personal information please see Data Protection and Privacy Procedure and the relevant Data Protection and Privacy Collection Statement that applies to you depending on the nature of your interaction with us.
If you have any questions about how Monash University is collecting and handling your personal information, please contact our Data Protection and Privacy Office at dataprotectionofficer@monash.edu.