Adversarial Machine Learning: Bayesian Perspectives

arXiv:2003.03546v2 Announce Type: replace-cross
Abstract: Adversarial Machine Learning (AML) is emerging as a major field aimed at protecting machine learning (ML) systems against security threats: in certain scenarios there may be adversaries that actively manipulate input data to fool learning systems. This creates a new class of security vulnerabilities that ML systems may face, and a new desirable property called adversarial robustness essential to trust operations based on ML outputs. Most work in AML is built upon a game-theoretic modelling …

abstract adversarial adversarial machine learning aml arxiv bayesian class cs.ai cs.lg data face learning systems machine machine learning major perspectives security security vulnerabilities stat.co stat.ml systems threats type vulnerabilities