activity
20242026
collaborators

10 papers

cs.AI2026

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…

cs.CL2026

Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions

Yongqi Li, Hao Lang, Tieyun Qian +1

Vision-language models are increasingly employed as multimodal conversational agents (MCAs) for diverse conversational tasks. Recently, reinforcement learning (RL) has been widely…

cs.LG2026

Understanding Generalization in Role-Playing Models via Information Theory

Yongqi Li, Hao Lang, Fei Huang +2

Role-playing models (RPMs) are widely used in real-world applications but underperform when deployed in the wild. This degradation can be attributed to distribution shifts, includi…

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…

cs.AI2025

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…

cs.CR2025

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations

Xiaohu Li, Yunfeng Ning, Zepeng Bao +3

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this se…