PoTS: Proof-of-Training-Steps for Backdoor Detection in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Seddik, Issam, Souihi, Sami, Tamaazousti, Mohamed, Piergiovanni, Sara Tucci
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning I.2.7; I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.15106