Collusion Resistant Watermarking for Deep Learning Models Protection
Authors:
- 13 February 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
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.Keywords
This publication has 7 references indexed in Scilit:
- Adversarial frontier stitching for remote neural network watermarkingNeural Computing and Applications, 2019
- Watermarking deep neural networks for embedded systems2018
- Protecting Intellectual Property of Deep Neural Networks with Watermarking2018
- Embedding Watermarks into Deep Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- Collusion-Resistant Watermarking Using Modified Barni Method2014
- Robust watermarking of still images for copyright protection2002