# Differentially Private 2D Human Pose Estimation

arXiv: https://arxiv.org/abs/2504.10190 · HTML: https://mlsanity.com/paper/2504.10190/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 80 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 30 of 50)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Differentially Private Fine-tuning of Language Models](https://mlsanity.com/paper/2110.06500/) (2021)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [TinyViT: Fast Pretraining Distillation for Small Vision Transformers](https://mlsanity.com/paper/2207.10666/) (2022)
- [Unlocking High-Accuracy Differentially Private Image Classification through Scale](https://mlsanity.com/paper/2204.13650/) (2022)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [A Dataset for Movie Description](https://mlsanity.com/paper/1501.02530/) (2015)
- [Distribution-Aware Coordinate Representation for Human Pose Estimation](https://mlsanity.com/paper/1910.06278/) (2019)
- [The Privacy Onion Effect: Memorization is Relative](https://mlsanity.com/paper/2206.10469/) (2022)
- [Reconstructing Training Data from Trained Neural Networks](https://mlsanity.com/paper/2206.07758/) (2022)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation](https://mlsanity.com/paper/1406.2984/) (2014)
- [TokenPose: Learning Keypoint Tokens for Human Pose Estimation](https://mlsanity.com/paper/2104.03516/) (2021)
- [Single-Stage Multi-Person Pose Machines](https://mlsanity.com/paper/1908.09220/) (2019)
- [Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification](https://mlsanity.com/paper/2007.03813/) (2020)
- [Differentially Private Model Publishing for Deep Learning](https://mlsanity.com/paper/1904.02200/) (2019)
- [SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation](https://mlsanity.com/paper/2107.03332/) (2021)
- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [Selective Differential Privacy for Language Modeling](https://mlsanity.com/paper/2108.12944/) (2021)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Mixed Differential Privacy in Computer Vision](https://mlsanity.com/paper/2203.11481/) (2022)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)

## Built on by (most cited first, 1 of 1)

- [Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy](https://mlsanity.com/paper/2610.02943/) (2026)

## Abstract (arXiv)

Human pose estimation (HPE) has become essential in numerous applications including healthcare, activity recognition, and human-computer interaction. However, the privacy implications of processing sensitive visual data present significant deployment barriers in critical domains. While traditional anonymization techniques offer limited protection and often compromise data utility for broader motion analysis, Differential Privacy (DP) provides formal privacy guarantees but typically degrades model performance when applied naively. In this work, we present the first comprehensive framework for differentially private 2D human pose estimation (2D-HPE) by applying Differentially Private Stochastic Gradient Descent (DP-SGD) to this task. To effectively balance privacy with performance, we adopt Projected DP-SGD (PDP-SGD), which projects the noisy gradients to a low-dimensional subspace. Next, we incorporate Feature Differential Privacy(FDP) to selectively privatize only sensitive features while retaining public visual cues. Finally, we propose a hybrid feature-projective DP framework that combines both approaches to balance privacy and accuracy for HPE. We evaluate our approach on the MPII dataset across varying privacy budgets, training strategies, and clipping norms. Our combined feature-projective method consistently outperforms vanilla DP-SGD and individual baselines, achieving up to 82.61% mean PCKh@0.5 at ε = 0.8, substantially closing the gap to the non-private performance. This work lays foundation for privacy-preserving human pose estimation in real-world, sensitive applications.