"Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Qin, Zhang, Zhexin, Li, Zhi, Sun, Limin
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2511.01287