Mental Models of Adversarial Machine Learning. (arXiv:2105.03726v3 [cs.CR] UPDATED)

Although machine learning is widely used in practice, little is known about
practitioners' understanding of potential security challenges. In this work, we
close this substantial gap and contribute a qualitative study focusing on
developers' mental models of the machine learning pipeline and potentially
vulnerable components. Similar studies have helped in other security fields to
discover root causes or improve risk communication. Our study reveals two
\facets of practitioners' mental models of machine learning security. Firstly,
practitioners often confuse machine learning …

adversarial machine machine learning mental