Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Makhija, Disha, Arivazhagan, Manoj Ghuhan, Kumar, Vinayshekhar Bannihatti, Gangadharaiah, Rashmi
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.05449