collaborators

9 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

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.AI2026

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…

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.LG2025

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs

Birong Pan, Mayi Xu, Qiankun Pi +4

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer…

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…