Watermarks for Generative Adversarial Network Based on Steganographic Invisible Backdoor
Authors:
- 1 July 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1211-1216
Abstract
Model watermarking has become an important solution to protect the intellectual property right (IPR) of deep neural networks (DNN) models. However, there are few researches on the IPR protection of generative adversarial networks (GAN), which are widely used to generate photorealistic images. In the current backdoor-based watermarking method for GAN models, the trigger pattern of the watermark is easy to be detected and invalidated by the adversary, which may fail to achieve IPR protection. To address this drawback, we propose a new GAN model watermarking method, where an invisible backdoor based on steganography is injected into the target GAN model as a watermark. Experimentally, the proposed method effectively trades off the performance of GAN on original task and the robustness of watermarking for removal attacks. Moreover, the generated triggers can effectively resist being detected by attackers.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 11 references indexed in Scilit:
- Imperceptible Backdoor Attack: From Input Space to Feature Representation2022
- Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attacks2021
- Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection2019
- Adversarial frontier stitching for remote neural network watermarkingNeural Computing and Applications, 2019
- Protecting Intellectual Property of Deep Neural Networks with Watermarking2018
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Embedding Watermarks into Deep Neural Networks2017
- Adversarial Diversity and Hard Positive Generation2016
- Multimedia watermarking techniquesProceedings of the IEEE, 1999
- Review of watermarking and the importance of perceptual modeling1997