all InfoSec news
Adversarial Machine Learning: A Systematic Survey of Backdoor Attack, Weight Attack and Adversarial Example. (arXiv:2302.09457v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Adversarial machine learning (AML) studies the adversarial phenomenon of
machine learning, which may make inconsistent or unexpected predictions with
humans. Some paradigms have been recently developed to explore this adversarial
phenomenon occurring at different stages of a machine learning system, such as
training-time adversarial attack (i.e., backdoor attack), deployment-time
adversarial attack (i.e., weight attack), and inference-time adversarial attack
(i.e., adversarial example). However, although these paradigms share a common
goal, their developments are almost independent, and there is still no big …
adversarial aml attack backdoor deployment humans machine machine learning may predictions studies survey system training