collaborators

5 papers

cs.CV2025

Fantastic Copyrighted Beasts and How (Not) to Generate Them

Luxi He, Yangsibo Huang, Weijia Shi +7

Recent studies show that image and video generation models can be prompted to reproduce copyrighted content from their training data, raising serious legal concerns about copyright…

cs.AI2025

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Tinghao Xie, Xiangyu Qi, Yi Zeng +13

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts…

cs.CR2024

On Evaluating the Durability of Safeguards for Open-Weight LLMs

Xiangyu Qi, Boyi Wei, Nicholas Carlini +7

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical sa…

cs.LG2024

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Boyi Wei, Kaixuan Huang, Yangsibo Huang +6

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This stu…

cs.CR2024

AI Risk Management Should Incorporate Both Safety and Security

Xiangyu Qi, Yangsibo Huang, Yi Zeng +22

The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety…