Dayong Ye (University of Technology Sydney), Tianqing Zhu (City University of Macau), Congcong Zhu (City University of Macau), Derui Wang (CSIRO’s Data61), Kun Gao (University of Technology Sydney), Zewei Shi (CSIRO’s Data61), Sheng Shen (Torrens University Australia), Wanlei Zhou (City University of Macau), Minhui Xue (CSIRO's Data61)

Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that has been largely overlooked in the research of unlearning is reinforcement learning. Reinforcement learning focuses on training an agent to make optimal decisions within an environment to maximize its cumulative rewards. During the training, the agent tends to memorize the features of the environment, which raises a significant concern about privacy. As per data protection regulations, the owner of the environment holds the right to revoke access to the agent's training data, thus necessitating the development of a novel and pressing research field, termed emph{reinforcement unlearning}. Reinforcement unlearning focuses on revoking entire environments rather than individual data samples. This unique characteristic presents three distinct challenges: 1) how to propose unlearning schemes for environments; 2) how to avoid degrading the agent's performance in remaining environments; and 3) how to evaluate the effectiveness of unlearning. To tackle these challenges, we propose two reinforcement unlearning methods. The first method is based on decremental reinforcement learning, which aims to erase the agent's previously acquired knowledge gradually. The second method leverages environment poisoning attacks, which encourage the agent to learn new, albeit incorrect, knowledge to remove the unlearning environment. Particularly, to tackle the third challenge, we introduce the concept of ``environment inference'' to evaluate the unlearning outcomes. The source code is available at url{https://github.com/cp-lab-uts/Reinforcement-Unlearning}.

View More Papers

Detecting Ransomware Despite I/O Overhead: A Practical Multi-Staged Approach

Christian van Sloun (RWTH Aachen University), Vincent Woeste (RWTH Aachen University), Konrad Wolsing (RWTH Aachen University & Fraunhofer FKIE), Jan Pennekamp (RWTH Aachen University), Klaus Wehrle (RWTH Aachen University)

Read More

AI-Assisted RF Fingerprinting for Identification of User Devices in...

Aishwarya Jawne (Center for Connected Autonomy & AI, Florida Atlantic University), Georgios Sklivanitis (Center for Connected Autonomy & AI, Florida Atlantic University), Dimitris A. Pados (Center for Connected Autonomy & AI, Florida Atlantic University), Elizabeth Serena Bentley (Air Force Research Laboratory)

Read More

Revisiting Concept Drift in Windows Malware Detection: Adaptation to...

Adrian Shuai Li (Purdue University), Arun Iyengar (Intelligent Data Management and Analytics, LLC), Ashish Kundu (Cisco Research), Elisa Bertino (Purdue University)

Read More

DLBox: New Model Training Framework for Protecting Training Data

Jaewon Hur (Seoul National University), Juheon Yi (Nokia Bell Labs, Cambridge, UK), Cheolwoo Myung (Seoul National University), Sangyun Kim (Seoul National University), Youngki Lee (Seoul National University), Byoungyoung Lee (Seoul National University)

Read More