Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations
In this paper, we consider privacy aspects of wireless federated learning (FL) with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. By exploiting the waveform superposition property of multiple access channels, OtA FL enables the users to transmit their updates simultaneously with linear processing techniques, which improves resource efficiency. However, this setting is vulnerable to privacy leakage since an adversary node can hear directly the uncoded message. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy due to the reduced signal-to-noise ratio. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server at the same time. More explicitly, spatially correlated perturbations are added to the gradient vectors at the users before transmission. Using the zero-sum property of the correlated perturbations, the side effect of the added perturbation on the aggregated gradients at the edge server can be minimized. In the meanwhile, the added perturbation will not be canceled out at the adversary, which prevents privacy leakage. Theoretical analysis of the perturbation covariance matrix, differential privacy, and model convergence is provided, based on which an optimization problem is formulated to jointly design the covariance matrix and the power scaling factor to balance between privacy protection and convergence performance. Simulation results validate the correlated perturbation approach can provide strong defense ability while guaranteeing high learning accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation
This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure agg…
Federated LearningTowards Explainable Federated Learning: Understanding the Impact of Differential Privacy
Data privacy and eXplainable Artificial Intelligence (XAI) are two important aspects for modern Machine Learning systems. To enhance data privacy, recent machine learning models have been designed as a Federated Learning…
Federated LearningResidue-based Label Protection Mechanisms in Vertical Logistic Regression
Federated learning (FL) enables distributed participants to collaboratively learn a global model without revealing their private data to each other. Recently, vertical FL, where the participants hold the same set of samp…
Federated LearningInference AttackregressionTS-Finder: privacy enhanced web crawler detection model using temporal–spatial access behaviors
Web crawler detection is critical for preventing unauthorized extraction of valuable information from websites. Current methods rely on heuristics, leading to time-consuming processes and the inability to detect novel c…
Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration
This paper proposes a data privacy protection framework based on federated learning, which aims to realize effective cross-domain data collaboration under the premise of ensuring data privacy through distributed learning…
Federated Learning