Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projection

TL;DR

This paper introduces a privacy-aware video anomaly detection method using orthogonal subspace projection to remove facial features while maintaining detection accuracy.

Contribution

It proposes the Guided Orthogonal Projection Layer (G-OPL) that suppresses facial attributes with weak supervision, enhancing privacy without sacrificing detection performance.

Findings

Embedding privacy constraints reduces sensitive information in representations.

The method maintains or improves anomaly detection accuracy.

The approach supports privacy-preserving video analysis in human-centered scenarios.

Abstract

Video anomaly detection (VAD) systems often prioritize accuracy while overlooking privacy concerns, limiting their suitability for real-world deployment. We propose the Orthogonal Projection Layer (OPL), a lightweight module that removes task-irrelevant variations to produce representations focused on anomaly-relevant cues. To address privacy risks in human-centered scenarios, we introduce Guided OPL (G-OPL), which suppresses facial attributes using weak supervision from face-presence signals while preserving non-identifying features such as pose and motion. A cosine alignment objective enforces consistent capture and removal of facial information without identity labels or adversarial training. We further present a privacy-aware evaluation framework that jointly assesses detection performance and privacy preservation, and enables analysis of how sensitive information is filtered. Experiments show that embedding privacy constraints into model design reduces sensitive information while maintaining or improving detection accuracy, supporting projection-based architectures as a principled approach for privacy-aware VAD.