4 papers
Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
Huilin Zhou, Ruoxi Cheng, Yuhang Wang +4
Diffusion models achieve strong performance in text-to-image generation, but they can still produce unsafe content. Training-free safety guidance offers a practical inference-time…
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
Huilin Zhou, Jian Zhao, Yilu Zhong +7
Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing approaches often rely on static…
TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations
Xiuyuan Chen, Jian Zhao, Yuxiang He +10
While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based atta…
RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration
Xiuyuan Chen, Jian Zhao, Yuchen Yuan +8
Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity…