5 papers
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…
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…
Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints
Zhengdong Lu, Weikai Lu, Yiling Tao +6
Despite significant advances in Large Language Models (LLMs), planning tasks still present challenges for LLM-based agents. Existing planning methods face two key limitations: heav…
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
Weikai Lu, Hao Peng, Huiping Zhuang +2
Multimodal Large Language Models (MLLMs) have serious security vulnerabilities.While safety alignment using multimodal datasets consisting of text and data of additional modalities…
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
Weikai Lu, Ziqian Zeng, Jianwei Wang +5
Jailbreaking attacks can enable Large Language Models (LLMs) to bypass the safeguard and generate harmful content. Existing jailbreaking defense methods have failed to address the…