DeepSniffer
Xing Hu, Ling Liang, Shuangchen Li, Lei Deng, Pengfei Zuo, Yu Ji, Xinfeng Xie, Yufei Ding, Chang Liu, Timothy Sherwood, Yuan Xie
Abstract
As deep neural networks (DNNs) continue their reach into a wide range of application domains, the neural network architecture of DNN models becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. Previous studies explore to leverage architecture-level events disposed in hardware platforms to extract the model architecture information. They pose the following limitations: requiring a priori knowledge of victim models, lacking in robustness and generality, or obtaining incomplete information of the victim model architecture.
Topics & Concepts
GeneralityComputer scienceLeverage (statistics)Robustness (evolution)ArchitectureA priori and a posterioriArtificial intelligenceDeep neural networksArtificial neural networkAdversarial systemNetwork architectureProperty (philosophy)Machine learningComputer securityBiochemistryPsychologyArtPhilosophyPsychotherapistChemistryVisual artsGeneEpistemologyAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsAdvanced Neural Network Applications