Towards Practical Watermark for Deep Neural Networks in Federated Learning

Abstract

With the wide application of deep neural networks, it is important to verify a host's possession over a deep neural network model and protect the model. To meet this goal, various mechanisms have been designed. By embedding extra information into a network and revealing it afterward, the watermark becomes a competitive candidate in proving integrity for deep learning systems. However, concurrent watermarking schemes can hardly be adopted for emerging distributed learning paradigms that raise extra requirements during the ownership verification. A spearheading distributed learning paradigm is federated learning (FL) where many parties participate in training one single model. Each author participating in the FL should be able to verify its ownership independently. Moreover, there are other potential threat and corresponding security requirements under this scenario. To meet those requirements, in this paper, we demonstrate a watermarking protocol for protecting deep neural networks in the setting of FL. By incorporating the state-of-the-art watermarking scheme and the cryptological primitive designed for distributed storage, the protocol meets the need for ownership verification in the FL scenario without violating the privacy for each participant. This work paves the way for generalizing watermark as a practical security mechanism for protecting deep learning models in distributed learning platforms.

arXiv commentNo comments

References in corpus (12)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Embedding Watermarks into Deep Neural Networks
• Mitigating Sybils in Federated Learning Poisoning
• Adversarial Frontier Stitching for Remote Neural Network Watermarking
• Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
• Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
• Piracy Resistant Watermarks for Deep Neural Networks
• Removing Backdoor-Based Watermarks in Neural Networks with Limited Data
• Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization
• Robust Watermarking of Neural Network with Exponential Weighting
• RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks
• Secure Watermark for Deep Neural Networks with Multi-task Learning

Cited by in corpus (2)

• Towards Traitor Tracing in Black-and-White-Box DNN Watermarking with Tardos-based Codes
• Regulating Ownership Verification for Deep Neural Networks: Scenarios, Protocols, and Prospects