5 papers
OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
Ming Wen, Kun Yang, Jingyu Zhang +4
While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or situational violations.…
Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models
Fengheng Chu, Jiahao Chen, Yuhong Wang +4
While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals limited understanding of components…
TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Mingxuan Zhang, Oubo Ma, Kang Wei +2
Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making applications, including robotics, healthcare, smart grids, and finan…
LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge
Songze Li, Chuokun Xu, Jiaying Wang +6
Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks, driving the development and widespread adoption of LLM-as-a-Judge systems for automate…
ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models
Jin Xie, Ruishi He, Songze Li +2
Parameter-efficient fine-tuning (PEFT) has emerged as a practical solution for adapting large language models (LLMs) to custom datasets with significantly reduced computational cos…