Industrial practitioners' mental models of adversarial machine learning

Lukas Bieringer (QuantPi), Kathrin Grosse (University of Cagliari), Michael Backes (CISPA Helmholtz Center for Information Security), Battista Biggio (University of Cagliari, Pluribus One), Katharina Krombholz (CISPA Helmholtz Center for Information Security)

Published May 8, 2021 · arXiv:2105.03726

cs.CRcs.AI

Abstract

The study explores the mental models of industrial practitioners regarding adversarial machine learning (AML), revealing a blurred distinction between AML and non-AML security, and a focus on workflows with potentially several models rather than individual models as in AML research.

arXiv abstract PDF