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

Oreo: Protecting ASLR Against Microarchitectural Attacks

Shixin Song (Massachusetts Institute of Technology), Joseph Zhang (Massachusetts Institute of Technology), Mengjia Yan (Massachusetts Institute of Technology)

Read More

Tweezers: A Framework for Security Event Detection via Event...

Jian Cui (Indiana University), Hanna Kim (KAIST), Eugene Jang (S2W Inc.), Dayeon Yim (S2W Inc.), Kicheol Kim (S2W Inc.), Yongjae Lee (S2W Inc.), Jin-Woo Chung (S2W Inc.), Seungwon Shin (KAIST), Xiaojing Liao (Indiana University)

Read More

ReThink: Reveal the Threat of Electromagnetic Interference on Power...

Fengchen Yang (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Zihao Dan (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Kaikai Pan (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Chen Yan (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Xiaoyu Ji (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Wenyuan Xu (Zhejiang University; ZJU…

Read More

Evaluating LLMs Towards Automated Assessment of Privacy Policy Understandability

Keika Mori (Deloitte Tohmatsu Cyber LLC, Waseda University), Daiki Ito (Deloitte Tohmatsu Cyber LLC), Takumi Fukunaga (Deloitte Tohmatsu Cyber LLC), Takuya Watanabe (Deloitte Tohmatsu Cyber LLC), Yuta Takata (Deloitte Tohmatsu Cyber LLC), Masaki Kamizono (Deloitte Tohmatsu Cyber LLC), Tatsuya Mori (Waseda University, NICT, RIKEN AIP)

Read More