A Statistical Method for Attack-Agnostic Adversarial Attack Detection with Compressive Sensing Comparison
This addresses the threat of adversarial attacks for ML practitioners by providing a reliable, attack-agnostic detection method, though it appears incremental as it builds on existing detection frameworks.
The paper tackles the problem of detecting adversarial attacks in machine learning systems by proposing a statistical method that uses a compressed/uncompressed neural network pair to generate a metric for adversarial presence, achieving near-perfect detection across various attack types and reducing false positives.
Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this work, we propose a statistical approach that establishes a detection baseline before a neural network's deployment, enabling effective real-time adversarial detection. We generate a metric of adversarial presence by comparing the behavior of a compressed/uncompressed neural network pair. Our method has been tested against state-of-the-art techniques, and it achieves near-perfect detection across a wide range of attack types. Moreover, it significantly reduces false positives, making it both reliable and practical for real-world applications.