Reverse-Engineering Deep Neural Networks Using Floating-Point Timing Side-Channels
Cheng Gongye, Yunsi Fei, Thomas Wahl
Abstract
Trained Deep Neural Network (DNN) models have become valuable intellectual property. A new attack surface has emerged for DNNs: model reverse engineering. Several recent attempts have utilized various common side channels. However, recovering DNN parameters, weights and biases, remains a challenge. In this paper, we present a novel attack that utilizes a floating-point timing side channel to reverse-engineer parameters of multi-layer perceptron (MLP) models in software implementation, entirely and precisely. To the best of our knowledge, this is the first work that leverages a floating-point timing side-channel for effective DNN model recovery.
Topics & Concepts
Reverse engineeringComputer scienceSide channel attackArtificial neural networkPerceptronDeep neural networksPoint (geometry)Deep learningChannel (broadcasting)SoftwareArtificial intelligenceProperty (philosophy)Floating pointComputer engineeringMachine learningAlgorithmTelecommunicationsProgramming languageEpistemologyMathematicsCryptographyGeometryPhilosophyAdversarial Robustness in Machine LearningAdvancements in Semiconductor Devices and Circuit DesignSecurity and Verification in Computing