Protecting Intellectual Property of Deep Neural Networks with Watermarking
| Autor: | Ian M. Molloy, Jialong Zhang, Marc Ph. Stoecklin, Heqing Huang, Hui Wu, Zhongshu Gu, Jiyong Jang |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Artificial neural network
Computer science business.industry Deep learning Inference 020206 networking & telecommunications Watermark 02 engineering and technology Machine learning computer.software_genre 0202 electrical engineering electronic engineering information engineering Key (cryptography) Benchmark (computing) 020201 artificial intelligence & image processing Artificial intelligence Pruning (decision trees) business Digital watermarking computer |
| Zdroj: | AsiaCCS |
| DOI: | 10.1145/3196494.3196550 |
| Popis: | Deep learning technologies, which are the key components of state-of-the-art Artificial Intelligence (AI) services, have shown great success in providing human-level capabilities for a variety of tasks, such as visual analysis, speech recognition, and natural language processing and etc. Building a production-level deep learning model is a non-trivial task, which requires a large amount of training data, powerful computing resources, and human expertises. Therefore, illegitimate reproducing, distribution, and the derivation of proprietary deep learning models can lead to copyright infringement and economic harm to model creators. Therefore, it is essential to devise a technique to protect the intellectual property of deep learning models and enable external verification of the model ownership. In this paper, we generalize the "digital watermarking'' concept from multimedia ownership verification to deep neural network (DNNs) models. We investigate three DNN-applicable watermark generation algorithms, propose a watermark implanting approach to infuse watermark into deep learning models, and design a remote verification mechanism to determine the model ownership. By extending the intrinsic generalization and memorization capabilities of deep neural networks, we enable the models to learn specially crafted watermarks at training and activate with pre-specified predictions when observing the watermark patterns at inference. We evaluate our approach with two image recognition benchmark datasets. Our framework accurately (100%) and quickly verifies the ownership of all the remotely deployed deep learning models without affecting the model accuracy for normal input data. In addition, the embedded watermarks in DNN models are robust and resilient to different counter-watermark mechanisms, such as fine-tuning, parameter pruning, and model inversion attacks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|