Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior
Weikai Lu, Ziqian Zeng, Kehua Zhang +5
Multimodal Large Language Models (MLLMs) are increasingly vulnerable to multimodal Indirect Prompt Injection (IPI) attacks, which embed malicious instructions in images, videos, or…
cs.CR2025
SDD: Self-Degraded Defense against Malicious Fine-tuning
Zixuan Chen, Weikai Lu, Xin Lin +1
Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLM…