Collusion Resistant Watermarking for Deep Learning Models Protection
Sayoko Kakikura, Hyunho Kang, Keiichi Iwamura · 2022 24th International Conference on Advanced Communication Technology (ICACT) · 2022
Deep learning has been used in many fields, such as image classification and data analysis. Training a high-performance model is expensive; thus, its property value is high. Watermarking is a representative technology providing intellectual property protection for models. In this study, we proposed white box watermarking using a modified Barni’s method (our previous study) for image watermarking. Our method is applicable to pre-trained models because the watermark is embedded in the parameters of the network without training. Additionally, the proposed method embeds multiple watermarking into neural networks using different keys. We evaluated the method using two different networks: 5-layer convolutional neural networks trained on MNIST and ResNet-50 trained on CIFAR-10 datasets. The experimental results show that our proposed approach can embed 10 watermarks with less than 0.1% loss of accuracy, and it detects them completely even after 90% of the parameters are pruned.