AIBearisharXiv – CS AI · 4h ago7/10
🧠
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
Researchers introduce MemJack, a multi-agent framework that exploits semantic vulnerabilities in Vision-Language Models through coordinated jailbreak attacks, achieving 71.48% attack success rates against Qwen3-VL-Plus. The study reveals that current VLM safety measures fail against sophisticated visual-semantic attacks and introduces MemJack-Bench, a dataset of 113,000+ attack trajectories to advance defensive research.