Collaborative Inference over Wireless Channels with Feature Differential Privacy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seif, Mohamed, Nie, Yuqi, Goldsmith, Andrea J., Poor, H. Vincent
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916455798276096
author Seif, Mohamed
Nie, Yuqi
Goldsmith, Andrea J.
Poor, H. Vincent
author_facet Seif, Mohamed
Nie, Yuqi
Goldsmith, Andrea J.
Poor, H. Vincent
contents Collaborative inference among multiple wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for sensing and computer vision. This approach typically involves a three-stage process: a) data acquisition through sensing, b) feature extraction, and c) feature encoding for transmission. However, transmitting the extracted features poses a significant privacy risk, as sensitive personal data can be exposed during the process. To address this challenge, we propose a novel privacy-preserving collaborative inference mechanism, wherein each edge device in the network secures the privacy of extracted features before transmitting them to a central server for inference. Our approach is designed to achieve two primary objectives: 1) reducing communication overhead and 2) ensuring strict privacy guarantees during feature transmission, while maintaining effective inference performance. Additionally, we introduce an over-the-air pooling scheme specifically designed for classification tasks, which provides formal guarantees on the privacy of transmitted features and establishes a lower bound on classification accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19917
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Collaborative Inference over Wireless Channels with Feature Differential Privacy
Seif, Mohamed
Nie, Yuqi
Goldsmith, Andrea J.
Poor, H. Vincent
Cryptography and Security
Information Theory
Machine Learning
Collaborative inference among multiple wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for sensing and computer vision. This approach typically involves a three-stage process: a) data acquisition through sensing, b) feature extraction, and c) feature encoding for transmission. However, transmitting the extracted features poses a significant privacy risk, as sensitive personal data can be exposed during the process. To address this challenge, we propose a novel privacy-preserving collaborative inference mechanism, wherein each edge device in the network secures the privacy of extracted features before transmitting them to a central server for inference. Our approach is designed to achieve two primary objectives: 1) reducing communication overhead and 2) ensuring strict privacy guarantees during feature transmission, while maintaining effective inference performance. Additionally, we introduce an over-the-air pooling scheme specifically designed for classification tasks, which provides formal guarantees on the privacy of transmitted features and establishes a lower bound on classification accuracy.
title Collaborative Inference over Wireless Channels with Feature Differential Privacy
topic Cryptography and Security
Information Theory
Machine Learning
url https://arxiv.org/abs/2410.19917