84 citations · 172 across the 43 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs
Shuailong Wang, Xinyu Lyu, Shengming Yuan +3
Token-Pruning accelerates Vision-Language Models by removing redundant visual tokens, yet its safety implications remain underexplored. In this work, we present the first comprehen…
cs.CR2025
SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
Beitao Chen, Xinyu Lyu, Lianli Gao +2
By incorporating visual inputs, Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning. However, this integration also introduces new vulnerabilities, mak…