activity
20242026
collaborators

10 papers

cs.CL2026

BiAxisBias: Evaluating LLM Bias Beyond a Single Prompt and a Single Explanation

Jialing Gan, Junhao Dong, Songze Li

LLM bias scores can depend on audit design. We introduce BiAxisBias, a prespecified audit varying task, role, perspective, sentiment, and wording over 200 stereotype statements whi…

cs.CR2026

MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization

Yongtong Gu, Songze Li, Xia Hu

The increasing misuse of AI-generated texts (AIGT) has motivated the rapid development of AIGT detection methods. However, the reliability of these detectors remains fragile agains…

cs.CR2026

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

Lei Ba, Qinbin Li, Songze Li

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains undere…

cs.CV2026

Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing

Yilong Huang, Songze Li

Diffusion-based face swapping achieves state-of-the-art performance, yet it also exacerbates the potential harm of malicious face swapping to violate portraiture right or undermine…

cs.CR2025

FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems

Yuzhen Long, Songze Li

Autonomous driving systems increasingly rely on multi-agent architectures powered by large language models (LLMs), where specialized agents collaborate to perceive, reason, and pla…

cs.CR2025

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning

Mingxuan Zhang, Oubo Ma, Kang Wei +2

Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making applications, including robotics, healthcare, smart grids, and finan…