Adversarial Machine Learning: Perspectives from Adversarial Risk Analysis

Título: Adversarial Machine Learning: Perspectives from Adversarial Risk Analysis

Ponente: David Rios (Real Academia de Ciencias)

Organizador: Joaquín Sánchez Soriano

Fecha: Martes 3 de noviembre de 2020 a las 12:00 horas.

Lugar:  Online. meet.google.com/hnj-bdpz-rft

Abstract: 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 modelling a conflict between an attacker and a defender. After reviewing game-theoretic approaches to AML, we discuss the benefits that adversarial risk analysis perspectives bring in when  defending ML based systems and identify relevant research directions.