Delete but Not Gone: Reactivation of Neural Network Watermarks
Open Access
- 20 March 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 17 (3) , 1-28
Abstract
As Deep Neural Networks (DNNs) become integral to critical applications, protecting their Intellectual Property (IP) has become paramount. Neural network watermarking is a technique that embeds unique identifiers into models, asserting ownership and deterring unauthorized use. However, sophisticated attacks can deactivate or remove these watermarks without significantly compromising model performance, undermining current protection strategies. In this article, we introduce the first method for reactivating deactivated neural network watermarks in altered DNN models without requiring access to the original model parameters or training data. By formulating the reactivation process as an optimization problem, we employ projected gradient descent to identify new trigger inputs that restore the embedded watermark. Regularization techniques are incorporated to ensure these triggers resemble legitimate inputs, enhancing both stealth and practicality. Through experiments on various benchmark datasets and model architectures, we demonstrate the effectiveness of our method against common model alterations, including fine-tuning, pruning, and surrogate model attacks. Our work addresses a critical gap in DNN IP protection, offering a robust and practical solution for watermark reactivation. This empowers model owners to assert their rights even in the face of advanced adversarial tactics.Keywords
This publication has 35 references indexed in Scilit:
- Exploring refined dual visual features cross-combination for image captioningNeural Networks, 2024
- Multidirectional Gradient Predictor for Region-Based Reversible Data Hiding in Encrypted ImagesIEEE Internet of Things Journal, 2024
- FedCRMW: Federated model ownership verification with compression-resistant model watermarkingExpert Systems with Applications, 2024
- PersistVerify: Federated model ownership verification with spatial attention and boundary samplingKnowledge-Based Systems, 2024
- Adaptive watermarking with self-mutual check parameters in deep neural networksPattern Recognition Letters, 2024
- Neural network laundering: Removing black-box backdoor watermarks from deep neural networksComputers & Security, 2021
- Removing Backdoor-Based Watermarks in Neural Networks with Limited Data2021
- Color Image Reversible Data Hiding With Double-Layer EmbeddingIEEE Access, 2020
- Quantization Networks2019
- Pruning algorithms-a surveyIEEE Transactions on Neural Networks, 1993