ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning
ATLAS-AL is a black-box, query-based red-teaming framework that treats adversarial example discovery as active-learning level-set estimation, using calibrated local/global trust-region sampling to find and then characterize whole regions of inputs that cause a model to fail. The nice idea is that it aims to recover representative adversarial sets rather than single attacks and reportedly beats NES, SignHunter, and Bayesian optimization under limited queries, though the evidence is mostly benchmark-driven and the method likely depends heavily on the quality of its calibration, latent/search space, and query budget.
Abstract
Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive mechanisms that can efficiently discover \textit{sets} of inputs that induce model failure. We introduce ATLAS (Adaptive Trust-Regions for Latent Adversarial Searches), which is a query-based framework that discovers adversarial input sets for black-box learning systems. ATLAS casts attack generation as an active learning level set estimation problem then combines calibrated approximations with a local-global sampling architecture to find regions of the input space that contain adversarial examples. Once discovered, ATLAS is designed to sample points within these adversarial regions to build adversarial sets that accurately represent the state of robustness of the target model. When applied on toy experiments, we find that ATLAS is able to recover more of the adversarial region under a limited query budget than does previous work. When applied to standard and adversarially trained MNIST, CIFAR, and ImageNet model targets, ATLAS produces better representative attacks than other query-based black-box attacks (NES, SignHunter, BayesOpt). ATLAS represents an automated red-teaming framework that can be used for both analyzing the robustness of learning-based systems under development and continuous auditing to see how the robustness of a system changes over time.