Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offs

• URL: http://arxiv.org/abs/2608.04501v1
• Date: Wed, 05 Aug 2026 06:38:11 GMT
• Title: Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offs
• Abstract summary: Video surveillance in public safety, healthcare, and smart environments has made continuous human monitoring routine, raising real risks to personal identity and appearance.<n>PPAR tackles the tension between the utility of video understanding and this exposure, and has drawn fast-growing interest.<n>Most catalog a single mechanism family, predate recent adversarial and hybrid work, or barely address evaluation.<n>We address this with a PRISMA-guided review of 32 peer-reviewed papers drawn from 885 screened records.<n>We contribute a two-dimensional privacy-space taxonomy, a formal threat model, a comparative trade-off analysis, the PPAR Unified Evaluation Protocol
• Score: 2.998571128008104
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey [9.47737368469032]
  We propose the NLP Privacy Risk Identification in Social Media framework, which evaluates vulnerabilities across six dimensions.<n>Our analysis shows that transformer models achieve F1-scores ranging from 0.58-0.84, but incur a 1% - 23% drop under privacy-preserving fine-tuning.<n>We advocate for stronger anonymization, privacy-aware learning, and fairness-driven training to enable ethical NLP in social media contexts.
  arXiv  Detail & Related papers  (2026-01-26T21:09:48Z)
• Privacy-Preserving Federated Learning with Verifiable Fairness Guarantees [0.0]
  Federated learning enables collaborative model training across distributed institutions without centralizing sensitive data.<n>This paper introduces CryptoFair-FL, a novel cryptographic framework providing the first verifiable fairness guarantees for federated learning systems.
  arXiv  Detail & Related papers  (2026-01-18T15:06:30Z)
• CLUE: Non-parametric Verification from Experience via Hidden-State Clustering [64.50919789875233]
  We show that correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations.<n>ClUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates.
  arXiv  Detail & Related papers  (2025-10-02T02:14:33Z)
• Benchmarking Fraud Detectors on Private Graph Data [70.4654745317714]
  Currently, many types of fraud are managed in part by automated detection algorithms that operate over graphs.<n>We consider the scenario where a data holder wishes to outsource development of fraud detectors to third parties.<n>Third parties submit their fraud detectors to the data holder, who evaluates these algorithms on a private dataset and then publicly communicates the results.<n>We propose a realistic privacy attack on this system that allows an adversary to de-anonymize individuals' data based only on the evaluation results.
  arXiv  Detail & Related papers  (2025-07-30T03:20:15Z)
• Conformal Prediction for Privacy-Preserving Machine Learning [83.88591755871734]
  Using AES-encrypted variants of the MNIST dataset, we demonstrate that Conformal Prediction methods remain effective even when applied directly in the encrypted domain.<n>Our work sets a foundation for principled uncertainty quantification in secure, privacy-aware learning systems.
  arXiv  Detail & Related papers  (2025-07-13T15:29:14Z)
• The Impact of Generalization Techniques on the Interplay Among Privacy, Utility, and Fairness in Image Classification [2.271910267215261]
  Recent research suggests that generalization techniques can improve the balance between privacy and utility.<n>We examine fairness in both private and non-private learning models trained on datasets with synthetic and real-world biases.<n>We introduce a new metric, named emphharmonic score, which combines accuracy, privacy, and fairness into a single measure.
  arXiv  Detail & Related papers  (2024-12-16T16:35:31Z)
• Locally Differentially Private Document Generation Using Zero Shot Prompting [61.20953109732442]
  We propose a locally differentially private mechanism called DP-Prompt to counter author de-anonymization attacks. When DP-Prompt is used with a powerful language model like ChatGPT (gpt-3.5), we observe a notable reduction in the success rate of de-anonymization attacks.
  arXiv  Detail & Related papers  (2023-10-24T18:25:13Z)
• Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging [47.99192239793597]
  We evaluated the effect of privacy-preserving training of AI models regarding accuracy and fairness compared to non-private training. Our study shows that -- under the challenging realistic circumstances of a real-life clinical dataset -- the privacy-preserving training of diagnostic deep learning models is possible with excellent diagnostic accuracy and fairness.
  arXiv  Detail & Related papers  (2023-02-03T09:49:13Z)
• SA-DPSGD: Differentially Private Stochastic Gradient Descent based on Simulated Annealing [25.25065807901922]
  Differentially private gradient descent is the most popular training method with differential privacy in image recognition. Existing DPSGD schemes lead to significant performance degradation, which prevents the application of differential privacy. We propose a simulated annealing-based differentially private gradient descent scheme (SA-DPSGD) which accepts a candidate update with a probability that depends on the update quality and on the number of iterations.
  arXiv  Detail & Related papers  (2022-11-14T09:20:48Z)
• No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy" [75.98836424725437]
  New methods designed to preserve data privacy require careful scrutiny. Failure to preserve privacy is hard to detect, and yet can lead to catastrophic results when a system implementing a privacy-preserving'' method is attacked.
  arXiv  Detail & Related papers  (2022-09-29T17:50:23Z)
• Mixed Differential Privacy in Computer Vision [133.68363478737058]
  AdaMix is an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset.
  arXiv  Detail & Related papers  (2022-03-22T06:15:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.