Training DNN Model with Secret Key for Model Protection
April Pyone, Maung Maung, Hitoshi Kiya
Abstract
In this paper, we propose a model protection method by using block-wise pixel shuffling with a secret key as a preprocessing technique to input images for the first time. The protected model is built by training with such preprocessed images. Experiment results show that the performance of the protected model is close to that of non-protected models when the key is correct, while the accuracy is severely dropped when an incorrect key is given, and the proposed model protection has enough robustness against fine-tuning attacks, while maintaining almost the same performance accuracy as that of using a nonprotected model.
Topics & Concepts
Computer scienceRobustness (evolution)Key (lock)ShufflingPreprocessorArtificial intelligencePixelBlock (permutation group theory)Computer visionData miningComputer securityMathematicsBiochemistryChemistryProgramming languageGeneGeometryAdversarial Robustness in Machine LearningDigital Media Forensic DetectionAdvanced Steganography and Watermarking Techniques