Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Yinghan, Wen, Juan, Peng, Wanli, Wu, Zhengxian, Zhang, Ziwei, Xue, Yiming
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.15848