Simeng Qin

TISR: Breaking Vision–Language Models via Text–Image Segmentation and Reassembly

Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search

Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

SAGE-CoT: Self-Adaptive Generated Chain-of-Thought for Jailbreaking

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG