PCPT and ACPT: Copyright Protection and Traceability Scheme for DNN Model
Deep neural networks (DNNs) have achieved tremendous success in artificial intelligence (AI) fields. However, DNN models can be easily illegally copied, redistributed, or abused by criminals, seriously damaging the interests of model inventers. Currently, the copyright protection of DNN models by neural network watermarking has been studied, but the establishment of a traceability mechanism for determining the authorized users of a leaked model is a new problem driven by the demand for AI services. Because the existing traceability mechanisms are used for models without watermarks, a small number of false positives is generated. Existing black-box active protection schemes have loose authorization control and are vulnerable to forgery attacks. Therefore, based on the idea of black-box neural network watermarking with the video framing and image perceptual hash algorithm, this study proposes a passive copyright protection and traceability framework PCPT using an additional class of DNN models, improving the existing traceability mechanism that yields a small number of false positives. Based on the authorization control strategy and image perceptual hash algorithm, using the authorization control center constructed using the detector and verifier, a DNN model active copyright protection and traceability framework ACPT is proposed. It realizes stricter authorization control, which establishes a strong connection between users and model owners, and improves the framework security. The key sample that is simultaneously generated does not affect the quality of the original image and supports traceability verification.
READ FULL TEXT