On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pichler, Georg, Romanelli, Marco, Manivannan, Divya Prakash, Krishnamurthy, Prashanth, Khorrami, Farshad, Garg, Siddharth
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2402.16926