Machine Beats Machine: Machine Learning Models to Defend Against Adversarial Attacks
This work addresses security vulnerabilities in machine learning systems for applications like image processing, though it appears incremental as it builds on existing adversarial defense methods.
The paper tackles defending against adversarial attacks by deploying a two-layered machine learning system to detect tampered data and solve domain-specific problems, with results showing that clustering algorithms, especially DBSCAN applied to structural similarity measures, achieved promising performance.
We propose using a two-layered deployment of machine learning models to prevent adversarial attacks. The first layer determines whether the data was tampered, while the second layer solves a domain-specific problem. We explore three sets of features and three dataset variations to train machine learning models. Our results show clustering algorithms achieved promising results. In particular, we consider the best results were obtained by applying the DBSCAN algorithm to the structured structural similarity index measure computed between the images and a white reference image.