3 papers
cs.CR2025
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
Rongzhe Wei, Peizhi Niu, Xinjie Shen +7
Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the p…
cs.CL2025
Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
Rongzhe Wei, Peizhi Niu, Hans Hao-Hsun Hsu +9
Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of i…
cs.LG2025
Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
Rongzhe Wei, Mufei Li, Mohsen Ghassemi +7
Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its r…