Lianli Gao

3 papers University of Electronic Science and Technology of China, Tsinghua University

• FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
• Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
• SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism