Zhenhong Zhou

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems

Resource Consumption Red-Teaming for Large Vision-Language Models

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models

BACKDOOR COLLAPSE: ELIMINATING UNKNOWN THREATS VIA KNOWN BACKDOOR AGGREGATION IN LANGUAGE MODELS

On the Role of Attention Heads in Large Language Model Safety

Reinforced Lifelong Editing for Language Models