3 papers
cs.CV2026
Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models
Liangsheng Liu, Si Chen, Jiamin Wu +5
Vision-Language Models (VLMs), such as CLIP, have shown strong zero-shot generalization but remain highly vulnerable to adversarial perturbations, posing serious risks in real-worl…
cs.CR2026
Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
Junke Zhang, Jianwei Wang, Sishuo Chen +3
Jailbreak attacks on large language models (LLMs) aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is important for…
cs.CR2025
Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
Biao Yi, Tiansheng Huang, Sishuo Chen +4
Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. Th…