Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
Jianhao Chen, Shiqin Wang, Haoyang Chen +4
Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual perception with text generation. Existing multimodal jailbreak attacks primaril…
cs.CL2026
ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations
Hankun Kang, Xin Miao, Jianhao Chen +5
Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social envi…