BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Shuaitong, Li, Renjue, Yu, Lijia, Zhang, Lijun, Liu, Zhiming, Jin, Gaojie
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2511.10714