Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rayhan, Naheed, Jahan, Sohely
Format:	Preprint
Published:	2026
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/2604.21860