# Video-DPRP: A Differentially Private Approach for Visual Privacy-Preserving Video Human Activity Recognition

arXiv: https://arxiv.org/abs/2503.02132 · HTML: https://mlsanity.com/paper/2503.02132/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 63 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 30 of 33)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition](https://mlsanity.com/paper/1708.07632/) (2017)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [AdaCliP: Adaptive Clipping for Private SGD](https://mlsanity.com/paper/1908.07643/) (2019)
- [Learning with User-Level Privacy](https://mlsanity.com/paper/2102.11845/) (2021)
- [Learning to Anonymize Faces for Privacy Preserving Action Detection](https://mlsanity.com/paper/1803.11556/) (2018)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)
- [AnonymousNet: Natural Face De-Identification with Measurable Privacy](https://mlsanity.com/paper/1904.12620/) (2019)
- [Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study](https://mlsanity.com/paper/1807.08379/) (2018)
- [SPAct: Self-supervised Privacy Preservation for Action Recognition](https://mlsanity.com/paper/2203.15205/) (2022)
- [Privacy-Preserving Human Activity Recognition from Extreme Low Resolution](https://mlsanity.com/paper/1604.03196/) (2016)
- [Adversarial Learning of Privacy-Preserving and Task-Oriented Representations](https://mlsanity.com/paper/1911.10143/) (2019)
- [Learning Privacy Preserving Encodings through Adversarial Training](https://mlsanity.com/paper/1802.05214/) (2018)
- [PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy](https://mlsanity.com/paper/2001.00561/) (2020)
- [Dynamic Differential-Privacy Preserving SGD](https://mlsanity.com/paper/2111.00173/) (2021)
- ["I need a better description'': An Investigation Into User Expectations For Differential Privacy](https://mlsanity.com/paper/2110.06452/) (2021)
- [Is Appearance Free Action Recognition Possible?](https://mlsanity.com/paper/2207.06261/) (2022)
- [Realistic Full-Body Anonymization with Surface-Guided GANs](https://mlsanity.com/paper/2201.02193/) (2022)
- [What Are the Chances? Explaining the Epsilon Parameter in Differential Privacy](https://mlsanity.com/paper/2303.00738/) (2023)
- [Privacy-Utility Trade-off of Linear Regression under Random Projections and Additive Noise](https://mlsanity.com/paper/1902.04688/) (2019)
- [Differentially Private Video Activity Recognition](https://mlsanity.com/paper/2306.15742/) (2023)

## Built on by (most cited first, 3 of 3)

- [Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication](https://mlsanity.com/paper/2603.21305/) (2026)
- [PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognition](https://mlsanity.com/paper/2604.00761/) (2026)
- [From Privacy to Generalization: Linear Max-Information Bounds for Differentially Private Learning Algorithms](https://mlsanity.com/paper/2605.26222/) (2026)

## Abstract (arXiv)

Considerable effort has been made in privacy-preserving video human activity recognition (HAR). Two primary approaches to ensure privacy preservation in Video HAR are differential privacy (DP) and visual privacy. Techniques enforcing DP during training provide strong theoretical privacy guarantees but offer limited capabilities for visual privacy assessment. Conversely methods, such as low-resolution transformations, data obfuscation and adversarial networks, emphasize visual privacy but lack clear theoretical privacy assurances. In this work, we focus on two main objectives: (1) leveraging DP properties to develop a model-free approach for visual privacy in videos and (2) evaluating our proposed technique using both differential privacy and visual privacy assessments on HAR tasks. To achieve goal (1), we introduce Video-DPRP: a Video-sample-wise Differentially Private Random Projection framework for privacy-preserved video reconstruction for HAR. By using random projections, noise matrices and right singular vectors derived from the singular value decomposition of videos, Video-DPRP reconstructs DP videos using privacy parameters (ε,δ) while enabling visual privacy assessment. For goal (2), using UCF101 and HMDB51 datasets, we compare Video-DPRP's performance on activity recognition with traditional DP methods, and state-of-the-art (SOTA) visual privacy-preserving techniques. Additionally, we assess its effectiveness in preserving privacy-related attributes such as facial features, gender, and skin color, using the PA-HMDB and VISPR datasets. Video-DPRP combines privacy-preservation from both a DP and visual privacy perspective unlike SOTA methods that typically address only one of these aspects.