7 papers
The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege
Luxi He, Xiangyu Qi, Michel Liao +4
The latest Audio Language Models (Audio LMs) process speech directly instead of relying on a separate transcription step. This shift preserves detailed information, such as intonat…
An Adversarial Perspective on Machine Unlearning for AI Safety
Jakub Åucki, Boyi Wei, Yangsibo Huang +3
Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazard…
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…
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…
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…
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…