On the 26th of August, a co-hosted webinar between the MORS Data Science and Artificial Intelligence Community of Practice and the INFORMS Military and Security Society was organized. In this webinar, Dr. David Rios from CSIC/ICMAT, Trustonomy partner, discusses Adversarial Machine Learning: Perspectives from Adversarial Risk Analysis. Adversarial Machine Learning (AML) is emerging as a major field aimed at the protection of automated ML systems against security threats. The majority of work in this area has built upon a game-theoretic framework by modeling a conflict between an attacker and a defender. After reviewing game-theoretic approaches to AML, the webinar discusses the benefits that adversarial risk analysis perspectives bring in when defending ML-based systems.
The webinar is now available for all here
