Demystifying Arch-hints for Model Extraction: An Attack in Unified Memory System

Abstract: The deep neural network (DNN) models are deemed confidential due to their unique value in expensive training efforts, privacy-sensitive training data, and proprietary network characteristics. Consequently, the model value raises incentive for adversary to steal the model for profits, such as the representative model extraction attack. Emerging attack can leverage timing-sensitive architecture-level events (i.e., Arch-hints) disclosed in hardware platforms to extract DNN model layer information accurately. In this paper, we take the first step to uncover the root cause of such Arch-hints and summarize the principles to identify them. We then apply these principles to emerging Unified Memory (UM) management system and identify three new Arch-hints caused by UM's unique data movement patterns. We then develop a new extraction attack, UMProbe. We also create the first DNN benchmark suite in UM and utilize the benchmark suite to evaluate UMProbe. Our evaluation shows that UMProbe can extract the layer sequence with an accuracy of 95% for almost all victim test models, which thus calls for more attention to the DNN security in UM system.