4 papers · 1 filter
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
Jianhao Chen, Haoyang Chen, Shiqin Wang +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…
Can a Small Model Learn to Look Before It Leaps? Dynamic Learning and Proactive Correction for Hallucination Detection
Zepeng Bao, Shen Zhou, Qiankun Pi +5
Hallucination in large language models (LLMs) remains a critical barrier to their safe deployment. For hallucination detection to be practical in real-world scenarios, the use of e…
RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
Jianhao Chen, Mayi Xu, Haoyang Chen +6
Large Reasoning Models (LRMs) face a distinct safety vulnerability: their internal reasoning chains may generate harmful content even when the final output appears benign. To addre…
Aligning VLM Assistants with Personalized Situated Cognition
Yongqi Li, Shen Zhou, Xiaohu Li +9
Vision-language models (VLMs) aligned with general human objectives, such as being harmless and hallucination-free, have become valuable assistants of humans in managing visual tas…