Zhengyue Zhao
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Latent Policy Guardrail (LPG), a novel framework that efficiently enforces dynamic safety policies for LLMs by compressing complex policy deliberation into a small set of latent tokens, achieving high accuracy with significantly reduced latency.
MaskForge is a novel, adaptive, black-box attack framework that significantly improves jailbreaking diffusion large language models (dLLMs) by treating red-teaming as an optimized search over reusable structural patterns.
Papers
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu, Minhui Xue +2 more
MaskForge is a novel, adaptive, black-box attack framework that significantly improves jailbreaking diffusion large language models (dLLMs) by treating red-teaming as an optimized search over reusable…