A Real-Time Privacy-Preserving Behavior Recognition System via Edge-Cloud Collaboration

TL;DR

This paper introduces a real-time, privacy-preserving behavior recognition system that uses edge-cloud collaboration and information theory to transform raw images into irreversibly abstract features, ensuring privacy while maintaining recognition accuracy.

Contribution

It proposes a novel edge-cloud architecture with source desensitization and irreversible feature mapping based on Information Bottleneck theory for privacy-preserving behavior recognition.

Findings

Achieves millisecond-level processing on edge devices.

Effectively prevents image reconstruction, ensuring privacy.

Maintains high accuracy in abnormal behavior detection.

Abstract

As intelligent sensing expands into high-privacy environments such as restrooms and changing rooms, the field faces a critical privacy-security paradox. Traditional RGB surveillance raises significant concerns regarding visual recording and storage, while existing privacy-preserving methods-ranging from physical desensitization to traditional cryptographic or obfuscation techniques-often compromise semantic understanding capabilities or fail to guarantee mathematical irreversibility against reconstruction attacks. To address these challenges, this study presents a novel privacy-preserving perception technology based on the AI Flow theoretical framework and an edge-cloud collaborative architecture. The proposed methodology integrates source desensitization with irreversible feature mapping. Leveraging Information Bottleneck theory, the edge device performs millisecond-level processing to transform raw imagery into abstract feature vectors via non-linear mapping and stochastic noise injection. This process constructs a unidirectional information flow that strips identity-sensitive attributes, rendering the reconstruction of original images impossible. Subsequently, the cloud platform utilizes multimodal family models to perform joint inference solely on these abstract vectors to detect abnormal behaviors. This approach fundamentally severs the path to privacy leakage at the architectural level, achieving a breakthrough from video surveillance to de-identified behavior perception and offering a robust solution for risk management in high-sensitivity public spaces.