DarkneTZ
Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Soteris Demetriou, Ilias Leontiadis, Andrea Cavallaro, Hamed Haddadi
Abstract
We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices) are equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy risks as models can leak information about their training data through effective membership inference attacks (MIAs).
Topics & Concepts
Computer scienceEdge deviceEnhanced Data Rates for GSM EvolutionVariety (cybernetics)InferenceLimit (mathematics)Edge computingConjunction (astronomy)Information sensitivityDeep neural networksComputer securityArtificial neural networkArtificial intelligenceCloud computingOperating systemAstronomyMathematical analysisMathematicsPhysicsAdversarial Robustness in Machine LearningPrivacy-Preserving Technologies in DataSecurity and Verification in Computing