4 papers
The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails
Shuo Shi, Rui Yin, Naen Xu +7
Multimodal guard models have emerged as critical safety components for screening content in vision-language systems. While adversarial research has extensively studied jailbreaking…
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
Rui Yin, Tianxu Han, Naen Xu +8
Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can di…
AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
Weiming Song, Xuan Xie, Ruiping Yin
Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, int…
Stability as a Liability:Systematic Breakdown of Linguistic Structure in LLMs
Xianzhe Meng, Qiangsheng Zeng, Ling Luo +7
Training stability is typically regarded as a prerequisite for reliable optimization in large language models. In this work, we analyze how stabilizing training dynamics affects th…