发表机构
Chung-Ang University; Ulsan National Institute of Science and Technology (UNIST); College of Art and Technology, Chung-Ang University（中央大学; 蔚山科学技术院; 中央大学艺术与技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究通过PRISMA指导的综述，梳理32篇PPAR论文，提出分类法、评估协议等，分析各方法权衡，指出评估不足，推动PPAR从原型向部署发展。
AI 中文摘要
公共安全、医疗保健及智能环境中的视频监控已使持续人类监测成为常规操作，这引发了个人身份与外观暴露的实际风险。隐私保护动作识别（PPAR）旨在解决视频理解的效用与这种暴露之间的矛盾，已获得日益增长的关注。然而，现有综述仍存在局限性：多数仅归类单一机制家族、未涵盖近期对抗性与混合工作、或几乎未涉及评估，导致文献碎片化，存在不兼容的威胁模型、不一致的指标及无共享评估标准。我们采用PRISMA指导的综述，基于筛选的885篇记录纳入2018-2026年间的32篇同行评审论文。方法分为五个家族：对抗学习（52%）、基于骨架的（20%）、密码学（12%）、差分隐私（8%）及混合（8%），各有不同的隐私、效用与效率权衡。评估是薄弱环节：仅10%的论文采用正式隐私定义，65%依赖临时指标，40%报告定义不一致的cMAP。权衡显著：骨架方法准确率约85%但丢失外观信息，对抗方法在中等隐私（cMAP 0.9至0.3-0.5）下保持近80%的效用，差分隐私常低于70%。更严苛条件的测试不足：不足15%的论文检查跨数据集泛化，低于10%测试自适应攻击者，实时边缘部署几乎未涉及。我们贡献了二维隐私空间分类法、正式威胁模型、比较权衡分析、PPAR统一评估协议及以基准标准化为核心的路线图。基于此，我们认为PPAR可从原型走向部署，其经验可延伸至人脸识别与医学成像领域。
英文摘要
Video surveillance in public safety, healthcare, and smart environments has made continuous human monitoring routine, raising real risks to personal identity and appearance. Privacy-preserving action recognition (PPAR) tackles the tension between the utility of video understanding and this exposure, and has drawn fast-growing interest. However, existing surveys remain narrow. Most catalog a single mechanism family, predate recent adversarial and hybrid work, or barely address evaluation. The result is a fragmented literature with incompatible threat models, inconsistent metrics, and no shared evaluation standard. We address this with a PRISMA-guided review of 32 peer-reviewed papers (2018--2026) drawn from 885 screened records. Methods sort into five families, namely adversarial learning (52%), skeleton-based (20%), cryptographic (12%), differential privacy (8%), and hybrid (8%), each with distinct privacy, utility, and efficiency trade-offs. Evaluation is the weak point. Only 10% of papers adopt a formal privacy definition, 65% rely on ad-hoc metrics, and 40% report an inconsistently defined cMAP. The trade-offs are steep. Skeleton methods reach about 85% accuracy but drop appearance, adversarial methods hold near 80% utility at moderate privacy (cMAP 0.9 to 0.3--0.5), and differential privacy often falls below 70%. Harder conditions stay under-tested, with fewer than 15% of papers checking cross-dataset generalization, under 10% testing adaptive attackers, and real-time edge deployment nearly untouched. We contribute a two-dimensional privacy-space taxonomy, a formal threat model, a comparative trade-off analysis, the PPAR Unified Evaluation Protocol, and a roadmap centered on benchmark standardization. With this grounding, we argue PPAR can move from prototypes toward deployment, with lessons extending to face recognition and medical imaging.
