2 citations · 6 across the 29 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
Minghui Li, Hao Zhang, Yechao Zhang +4
Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address th…
cs.AI2024★ 1 cited
DarkSAM: Fooling Segment Anything Model to Segment Nothing
Ziqi Zhou, Yufei Song, Minghui Li +5
Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of…