Adaptive White-Box Watermarking with Self-Mutual Check Parameters in Deep Neural Networks
Not on the map. Why?
Abstract (arXiv)
Artificial Intelligence (AI) has found wide application, but also poses risks due to unintentional or malicious tampering during deployment. Regular checks are therefore necessary to detect and prevent such risks. Fragile watermarking is a technique used to identify tampering in AI models. However, previous methods have faced challenges including risks of omission, additional information transmission, and inability to locate tampering precisely. In this paper, we propose a method for detecting tampered parameters and bits, which can be used to detect, locate, and restore parameters that have been tampered with. We also propose an adaptive embedding method that maximizes information capacity while maintaining model accuracy. Our approach was tested on multiple neural networks subjected to attacks that modified weight parameters, and our results demonstrate that our method achieved great recovery performance when the modification rate was below 20%. Furthermore, for models where watermarking significantly affected accuracy, we utilized an adaptive bit technique to recover more than 15% of the accuracy loss of the model.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 22 Aug 2023.
Builds on
11 of 25 references.
References · 11
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
- 2017Embedding Watermarks into Deep Neural Networkscited by 227
- 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 82
- 2021A survey of deep neural network watermarking techniquescited by 69
- 2021RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recoverycited by 18
- 2021Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authenticationcited by 17
- 2021AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryptioncited by 11
- 2022Neural network fragile watermarking with no model performance degradationcited by 7
- 2019Survey of Attacks and Defenses on Edge-Deployed Neural Networkscited by 5
Built on by
Not cited yet.