AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning

by   Yusuke Koda, et al.

Wireless channels can be inherently privacy-preserving by distorting the received signals due to channel noise, and superpositioning multiple signals over-the-air. By harnessing these natural distortions and superpositions by wireless channels, we propose a novel privacy-preserving machine learning (ML) framework at the network edge, coined over-the-air mixup ML (AirMixML). In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and superpositioned samples. AirMixML coincides with model training using mixup data augmentation achieving comparable accuracy to that with raw data samples. From a privacy perspective, AirMixML is a differentially private (DP) mechanism limiting the disclosure of each worker's private sample information at the server, while the worker's transmit power determines the privacy disclosure level. To this end, we develop a fractional channel-inversion power control (PC) method, α-Dirichlet mixup PC (DirMix(α)-PC), wherein for a given global power scaling factor after channel inversion, each worker's local power contribution to the superpositioned signal is controlled by the Dirichlet dispersion ratio α. Mathematically, we derive a closed-form expression clarifying the relationship between the local and global PC factors to guarantee a target DP level. By simulations, we provide DirMix(α)-PC design guidelines to improve accuracy, privacy, and energy-efficiency. Finally, AirMixML with DirMix(α)-PC is shown to achieve reasonable accuracy compared to a privacy-violating baseline with neither superposition nor PC.



page 1

page 2

page 3

page 4

page 5

page 6


Production of Categorical Data Verifying Differential Privacy: Conception and Applications to Machine Learning

Private and public organizations regularly collect and analyze digitaliz...

Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform

Companies increasingly expose machine learning (ML) models trained over ...

Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning

Wireless connectivity is instrumental in enabling scalable federated lea...

Impact of Social Learning on Privacy-Preserving Data Collection

We study a model where a data collector obtains data from users through ...

Multi-hop Federated Private Data Augmentation with Sample Compression

On-device machine learning (ML) has brought about the accessibility to a...

Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise

Over-the-air computation (AirComp)-based federated learning (FL) enables...

Revisiting Analog Over-the-Air Machine Learning: The Blessing and Curse of Interference

We study a distributed machine learning problem carried out by an edge s...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.