Privacy-Preserving Detection Method for Transmission Line Based on Edge Collaboration

TL;DR

This paper introduces SecYOLOv7, a privacy-preserving object detection model for transmission lines using secure multi-party computation, enabling collaborative edge processing without compromising sensitive image data.

Contribution

The paper presents a novel secure detection framework based on MPC that enhances privacy in UAV-based transmission line inspection.

Findings

Secure protocols reduce privacy risks in edge detection.

Framework outperforms existing methods in efficiency and accuracy.

Secure collaborative detection maintains high detection performance.

Abstract

Unmanned aerial vehicles (UAVs) are commonly used for edge collaborative computing in current transmission line object detection, where computationally intensive tasks generated by user nodes are offloaded to more powerful edge servers for processing. However, performing edge collaborative processing on transmission line image data may result in serious privacy breaches. To address this issue, we propose a secure single-stage detection model called SecYOLOv7 that preserves the privacy of object detecting. Based on secure multi-party computation (MPC), a series of secure computing protocols are designed for the collaborative execution of Secure Feature Contraction, Secure Bounding-Box Prediction and Secure Object Classification by two non-edge servers. Performance evaluation shows that both computational and communication overhead in this framework as well as calculation error significantly outperform existing works.