Keywords: Threat Model, Economics, Cybersecurity, Machine Learning, Research, Practice
TL;DR: We present three case studies from the real world, derive trends and blind spots from all recent papers published in top security conferences, and state four actionable positions for more impactful adversarial ML research.
Abstract: Recent years have seen a proliferation of research on adversarial machine learning. Numerous papers demonstrate powerful algorithmic attacks against a wide variety of machine learning (ML) models, and numerous other papers propose defenses that can withstand most attacks. However, abundant real-world evidence suggests that actual attackers use simple tactics to subvert ML-driven systems, and as a result security practitioners have not prioritized adversarial ML defenses. Motivated by the apparent gap between researchers and practitioners, this position paper aims to bridge these two domains. We first present three real-world case studies from which we can glean practical insights unknown or neglected in research. Next, we analyze all adversarial ML papers recently published in top security conferences and highlight positive trends and blind spots. Finally, we state positions on precise and cost-driven threat modeling, collaboration between industry and academia, and reproducible research. If adopted, our positions will increase the real-world impact of future endeavours in adversarial ML, bringing both researchers and practitioners closer to their shared goal of improving the security of ML systems.