Microsoft, in collaboration with MITRE, IBM, NVIDIA, and Bosch, has released a new open framework that aims to help security analysts detect, respond to, and remediate adversarial attacks against machine learning (ML) systems.
Called the Adversarial ML Threat Matrix, the initiative is an attempt to organize the different techniques employed by malicious adversaries in subverting ML systems.
Just
Source de l’article sur The Hacker News
