Mixer: DNN Watermarking using Image Mixup
This addresses intellectual property protection for DNN model owners, but it is incremental as it builds on existing watermarking techniques with a specific trigger generation approach.
The paper tackles protecting DNN intellectual property by proposing a watermarking method using image Mixup to generate infinite triggers, achieving adequate security and robustness in experiments on image classification models.
It is crucial to protect the intellectual property rights of DNN models prior to their deployment. The DNN should perform two main tasks: its primary task and watermarking task. This paper proposes a lightweight, reliable, and secure DNN watermarking that attempts to establish strong ties between these two tasks. The samples triggering the watermarking task are generated using image Mixup either from training or testing samples. This means that there is an infinity of triggers not limited to the samples used to embed the watermark in the model at training. The extensive experiments on image classification models for different datasets as well as exposing them to a variety of attacks, show that the proposed watermarking provides protection with an adequate level of security and robustness.