arXiv 2605.086512026-05-09cs.CVcs.AIcs.LG

通过正交子空间投影实现隐私感知的视频异常检测

Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projection

School of Engineering and Built Environment, Griffith University（格里菲斯大学工程与环境学院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）

Lei Wang, Wenxiang Diao, Andrew Busch, Jun Zhou, Yongsheng Gao

备注：: Accepted as a Spotlight paper at the Forty-Third International Conference on Machine Learning (ICML 2026)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出正交投影层（OPL）和引导OPL（G-OPL），通过去除无关变化提升异常检测相关特征，同时抑制面部属性以保护隐私，实验表明隐私约束能减少敏感信息并保持检测精度。

摘要：

视频异常检测（VAD）系统常优先准确率而忽视隐私问题，限制了实际应用。我们提出正交投影层（OPL），一个轻量模块，通过去除任务无关变化生成关注异常相关线索的表示。为应对以人为中心场景的隐私风险，我们引入引导OPL（G-OPL），利用面部存在信号的弱监督抑制面部属性，同时保留非标识性特征如姿态和运动。余弦对齐目标强制一致捕捉和去除面部信息，无需身份标签或对抗训练。我们进一步提出一个隐私感知评估框架，联合评估检测性能和隐私保护，并分析敏感信息如何被过滤。实验表明，将隐私约束嵌入模型设计可减少敏感信息同时保持或提升检测精度，支持投影架构作为隐私感知VAD的原理性方法。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。