LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy

Abstract

Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data. One way to achieve a strict privacy guarantee is to apply local differential privacy into federated learning. However, previous works do not give a practical solution due to three issues. First, the noisy data is close to its original value with high probability, increasing the risk of information exposure. Second, a large variance is introduced to the estimated average, causing poor accuracy. Last, the privacy budget explodes due to the high dimensionality of weights in deep learning models. In this paper, we proposed a novel design of local differential privacy mechanism for federated learning to address the abovementioned issues. It is capable of making the data more distinct from its original value and introducing lower variance. Moreover, the proposed mechanism bypasses the curse of dimensionality by splitting and shuffling model updates. A series of empirical evaluations on three commonly used datasets, MNIST, Fashion-MNIST and CIFAR-10, demonstrate that our solution can not only achieve superior deep learning performance but also provide a strong privacy guarantee at the same time.

arXiv commentAccepted by IJCAI-21

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Learning Differentially Private Recurrent Language Models
• Differentially Private Federated Learning: A Client Level Perspective
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• Protection Against Reconstruction and Its Applications in Private Federated Learning
• Collecting and Analyzing Data from Smart Device Users with Local Differential Privacy
• Federated Model Distillation with Noise-Free Differential Privacy
• Wireless Federated Learning with Local Differential Privacy
• Private Model Compression via Knowledge Distillation

Cited by in corpus (9)

• A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysis
• Vision-Language Models for Edge Networks: A Comprehensive Survey
• Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
• Federated Model Distillation with Noise-Free Differential Privacy
• Secure Deep Graph Generation with Link Differential Privacy
• Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communication
• Fair and Differentially Private Distributed Frequency Estimation
• Understanding the Interplay between Privacy and Robustness in Federated Learning
• Differential Privacy Meets Federated Learning under Communication Constraints