3 papers
cs.CR2026
Stealthy Multi-Task Adversarial Attacks
Jiacheng Guo, Tianyun Zhang, Lei Li +3
Deep neural networks are highly vulnerable to adversarial perturbations, raising serious safety concerns in the real-world systems. While prior work mainly explores single-task att…
cs.AI2026
How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation
Hao Yang, Qinghua Zhao, Lei Li +2
Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanisms remain poorly understood. We analyze CoT's operational principles by reversely…
cs.AI2024
Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
Hao Yang, Qianghua Zhao, Lei Li
Chain-of-Thought prompting has significantly enhanced the reasoning capabilities of large language models, with numerous studies exploring factors influencing its performance. Howe…