Threats, attacks, and defenses in machine unlearning: A survey

Z Liu, H Ye, C Chen, Y Zheng, KY Lam - arxiv preprint arxiv:2403.13682, 2024 - arxiv.org
Machine Unlearning (MU) has recently gained considerable attention due to its potential to
achieve Safe AI by removing the influence of specific data from trained Machine Learning …

The emerged security and privacy of llm agent: A survey with case studies

F He, T Zhu, D Ye, B Liu, W Zhou, PS Yu - arxiv preprint arxiv:2407.19354, 2024 - arxiv.org
Inspired by the rapid development of Large Language Models (LLMs), LLM agents have
evolved to perform complex tasks. LLM agents are now extensively applied across various …

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?

S Wang, T Zhu, D Ye, W Zhou - arxiv preprint arxiv:2410.15267, 2024 - arxiv.org
The deployment of large language models (LLMs) like ChatGPT and Gemini has shown
their powerful natural language generation capabilities. However, these models can …

TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents

C Gong, K Li, J Yao, T Wang - arxiv preprint arxiv:2404.12530, 2024 - arxiv.org
Reinforcement learning (RL) trains an agent from experiences interacting with the
environment. In scenarios where online interactions are impractical, offline RL, which trains …

Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning

D Ye, T Zhu, J Li, K Gao, B Liu, LY Zhang… - arxiv preprint arxiv …, 2025 - arxiv.org
Duplication is a prevalent issue within datasets. Existing research has demonstrated that the
presence of duplicated data in training datasets can significantly influence both model …

Evaluating of Machine Unlearning: Robustness Verification Without Prior Modifications

H Xu, T Zhu, W Zhou - arxiv preprint arxiv:2410.10120, 2024 - arxiv.org
Machine unlearning, a process enabling pre-trained models to remove the influence of
specific training samples, has attracted significant attention in recent years. While extensive …