Collaborative Inference over Wireless Channels with Feature Differential Privacy

TL;DR

This paper proposes a privacy-preserving collaborative inference framework for wireless edge devices that reduces communication costs and guarantees privacy during feature transmission, with a novel over-the-air pooling scheme for classification.

Contribution

It introduces a new mechanism for secure feature transmission in wireless collaborative inference, balancing privacy, communication efficiency, and inference accuracy.

Findings

Achieves formal privacy guarantees for feature transmission.

Provides a lower bound on classification accuracy with the proposed scheme.

Reduces communication overhead in wireless edge inference.

Abstract

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.