Search papers, labs, and topics across Lattice.
This paper conducts a comprehensive PRISMA-guided review of 32 peer-reviewed studies on privacy-preserving action recognition (PPAR), identifying five distinct methodological families: adversarial learning, skeleton-based, cryptographic, differential privacy, and hybrid approaches. The authors highlight significant gaps in the literature, particularly in formal privacy definitions and evaluation metrics, revealing that only 10% of studies adopt a formal privacy definition and many rely on inconsistent metrics. The findings underscore the steep trade-offs in privacy and utility across methods, suggesting a need for standardized benchmarks to facilitate the transition of PPAR from theoretical frameworks to practical applications in fields like surveillance and healthcare.
The fragmented landscape of privacy-preserving action recognition reveals that only 10% of studies define privacy formally, raising questions about the reliability of existing evaluations.
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.
