4 papers
Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models
Zhengnan Guo, Fei Tan
While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically reg…
TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
Zhen Guo, Shanghao Shi, Hao Li +3
The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, th…
DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
Zhen Guo, Shanghao Shi, Shamim Yazdani +2
With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their compl…
Persistent Backdoor Attacks in Continual Learning
Zhen Guo, Abhinav Kumar, Reza Tourani
Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially…