Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Kulkarni, Prashant
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/2604.28129