Intriguing Properties of Adversarial ML Attacks in the Problem Space [Extended Version]

arXiv:1911.02142v3 Announce Type: replace
Abstract: Recent research efforts on adversarial machine learning (ML) have investigated problem-space attacks, focusing on the generation of real evasive objects in domains where, unlike images, there is no clear inverse mapping to the feature space (e.g., software). However, the design, comparison, and real-world implications of problem-space attacks remain underexplored. This article makes three major contributions. Firstly, we propose a general formalization for adversarial ML evasion attacks in the problem-space, which includes the definition of a …

adversarial arxiv attacks clear cs.cr cs.lg design domains evasive feature images machine machine learning mapping problem real research software space version world