Yinpeng Dong

Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information

Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention

Unveiling the Basin-Like Loss Landscape in Large Language Models

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems

Exploring Recursive Doubt in Large Language Models

Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models

Towards the Worst-case Robustness of Large Language Models

STAIR: Improving Safety Alignment with Introspective Reasoning

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling

Mitigating Overthinking in Large Reasoning Models via Manifold Steering

Towards Mitigating Factual Hallucination in LLMs through Self-Alignment with Memory

Adaptive Strategy Evolution for Generating Tailored Jailbreak Prompts against Black-Box Safety-Aligned LLMs