collaborators

10 papers

cs.AI2026

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs

Yang Luo, Xinran Liu, Tiantian Ji +3

Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term this phenomenon Structural Cog…

cs.CR2026

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Zenghao Duan, Yuxin Tian, Zhiyi Yin +6

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to t…

cs.CL2026

from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors

Yu Yan, Sheng Sun, Zenghao Duan +5

Current studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. However, they overlook that the direct generation of harmful…

cs.IR2026

PersonaAct: Simulating Short-Video Users with Personalized Agents for Counterfactual Filter Bubble Auditing

Shilong Zhao, Qinggang Yang, Zhiyi Yin +4

Short-video platforms rely on personalized recommendation, raising concerns about filter bubbles that narrow content exposure. Auditing such phenomena at scale is challenging becau…

cs.LG2026

Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification

Zenghao Duan, Zhiyi Yin, Zhichao Shi +8

Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g.…

cs.AI2026

Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models

Zenghao Duan, Liang Pang, Zihao Wei +6

Despite the success of test-time scaling, Large Reasoning Models (LRMs) frequently encounter repetitive loops that lead to computational waste and inference failure. In this paper,…