10 papers
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…
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…
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…
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…
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…
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…