Differentially Private 2D Human Pose Estimation

• URL: http://arxiv.org/abs/2504.10190v3
• Date: Fri, 10 Oct 2025 14:14:33 GMT
• Title: Differentially Private 2D Human Pose Estimation
• Authors: Kaushik Bhargav Sivangi, Paul Henderson, Fani Deligianni,
• Abstract summary: We present the first comprehensive framework for differentially private 2D human pose estimation (2D-HPE)<n>To effectively balance privacy performance, we adopt Projected DP-SGD, which projects the noisy gradients to a low-dimensional subspace.<n>Next, we incorporate Feature Differential Privacy(FDP) to selectively privatize only sensitive features while retaining public visual cues.
• Score: 6.982542225631412
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 $\epsilon = 0.8$, substantially closing the gap to the non-private performance. This work lays foundation for privacy-preserving human pose estimation in real-world, sensitive applications.

Related papers

• A General Framework for Per-record Differential Privacy [10.959311645622632]
  Per-record Differential Privacy (PrDP) addresses this by defining the privacy budget as a function of each record.<n>Existing solutions either handle specific privacy functions or adopt relaxed PrDP definitions.<n>We propose a general and practical framework that enables any standard DP mechanism to support PrDP.
  arXiv  Detail & Related papers  (2025-11-24T11:44:10Z)
• FusionDP: Foundation Model-Assisted Differentially Private Learning for Partially Sensitive Features [17.945111987608865]
  In practical scenarios, privacy protection may be required for only a subset of features.<n>Traditional DP-SGD enforces privacy protection on all features in one sample, leading to excessive noise injection and significant utility degradation.<n>We propose FusionDP, a two-step framework that enhances model utility under feature-level differential privacy.
  arXiv  Detail & Related papers  (2025-11-05T19:13:10Z)
• Private Hyperparameter Tuning with Ex-Post Guarantee [98.43027866582979]
  " Utility-first" privacy mechanisms prioritize a desired level of utility and then determine the corresponding privacy cost.<n>We extend the work of Wu et al. [ 2019] and Liu and Talwar [ 2019] to support any sequence of private estimators.<n>We demonstrate that hyper parameter tuning for these estimators, including the selection of an optimal privacy budget, can be performed without additional privacy cost.
  arXiv  Detail & Related papers  (2025-08-21T02:42:23Z)
• Machine Learning with Privacy for Protected Attributes [56.44253915927481]
  We refine the definition of differential privacy (DP) to create a more general and flexible framework that we call feature differential privacy (FDP)<n>Our definition is simulation-based and allows for both addition/removal and replacement variants of privacy, and can handle arbitrary separation of protected and non-protected features.<n>We apply our framework to various machine learning tasks and show that it can significantly improve the utility of DP-trained models when public features are available.
  arXiv  Detail & Related papers  (2025-06-24T17:53:28Z)
• Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks? [8.189149471520542]
  Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks. Although differential privacy (DP) offers strong theoretical guarantees against such leakage, its empirical privacy effectiveness on LLMs remains unclear. This paper systematically investigates the impact of DP across fine-tuning methods and privacy budgets.
  arXiv  Detail & Related papers  (2025-04-28T05:34:53Z)
• Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings [23.687702204151872]
  Textual Inversion (TI) learns an embedding vector for an image or set of images, to enable adaptation under differential privacy constraints.<n>We show DPAgg-TI outperforms DP-SGD finetuning in both utility and robustness under the same privacy budget.
  arXiv  Detail & Related papers  (2024-11-22T00:09:49Z)
• Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy [55.357715095623554]
  Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. We propose a Bayesian framework, Bayesian Coordinate Differential Privacy (BCDP), that enables feature-specific privacy quantification.
  arXiv  Detail & Related papers  (2024-10-24T03:39:55Z)
• Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy [64.32494202656801]
  Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence.<n>We present anonymization pipeline that replaces sensitive human subjects in video datasets with synthetic avatars within context.<n>We also proposeMaskDP to protect non-anonymized but privacy sensitive background information.
  arXiv  Detail & Related papers  (2024-10-22T15:22:53Z)
• Scalable Differential Privacy Mechanisms for Real-Time Machine Learning Applications [0.0]
  Large language models (LLMs) are increasingly integrated into real-time machine learning applications, where safeguarding user privacy is paramount. Traditional differential privacy mechanisms often struggle to balance privacy and accuracy, particularly in fast-changing environments with continuously flowing data. We introduce Scalable Differential Privacy (SDP), a framework tailored for real-time machine learning that emphasizes both robust privacy guarantees and enhanced model performance.
  arXiv  Detail & Related papers  (2024-09-16T20:52:04Z)
• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• Differentially Private Fine-Tuning of Diffusion Models [22.454127503937883]
  The integration of Differential Privacy with diffusion models (DMs) presents a promising yet challenging frontier. Recent developments in this field have highlighted the potential for generating high-quality synthetic data by pre-training on public data. We propose a strategy optimized for private diffusion models, which minimizes the number of trainable parameters to enhance the privacy-utility trade-off.
  arXiv  Detail & Related papers  (2024-06-03T14:18:04Z)
• Provable Privacy with Non-Private Pre-Processing [56.770023668379615]
  We propose a general framework to evaluate the additional privacy cost incurred by non-private data-dependent pre-processing algorithms. Our framework establishes upper bounds on the overall privacy guarantees by utilising two new technical notions.
  arXiv  Detail & Related papers  (2024-03-19T17:54:49Z)
• Pre-training Differentially Private Models with Limited Public Data [54.943023722114134]
  differential privacy (DP) is a prominent method to gauge the degree of security provided to the models. DP is yet not capable of protecting a substantial portion of the data used during the initial pre-training stage. We develop a novel DP continual pre-training strategy using only 10% of public data. Our strategy can achieve DP accuracy of 41.5% on ImageNet-21k, as well as non-DP accuracy of 55.7% and and 60.0% on downstream tasks Places365 and iNaturalist-2021.
  arXiv  Detail & Related papers  (2024-02-28T23:26:27Z)
• Personalized Differential Privacy for Ridge Regression [3.4751583941317166]
  We introduce our novel Personalized-DP Output Perturbation method ( PDP-OP) that enables to train Ridge regression models with individual per data point privacy levels. We provide rigorous privacy proofs for our PDP-OP as well as accuracy guarantees for the resulting model. We show that PDP-OP outperforms the personalized privacy techniques of Jorgensen et al.
  arXiv  Detail & Related papers  (2024-01-30T16:00:14Z)
• Sparsity-Preserving Differentially Private Training of Large Embedding Models [67.29926605156788]
  DP-SGD is a training algorithm that combines differential privacy with gradient descent. Applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. We present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.
  arXiv  Detail & Related papers  (2023-11-14T17:59:51Z)
• Personalized DP-SGD using Sampling Mechanisms [5.50042037663784]
  We extend Differentially Private Gradient Descent (DP-SGD) to support a recent privacy notion called ($Phi$,$Delta$)- Personalized Differential Privacy (($Phi$,$Delta$)- PDP. Our algorithm uses a multi-round personalized sampling mechanism and embeds it within the DP-SGD iteration. Experiments on real datasets show that our algorithm outperforms DP-SGD and simple combinations of DP-SGD with existing PDP mechanisms.
  arXiv  Detail & Related papers  (2023-05-24T13:56:57Z)
• Dynamic Differential-Privacy Preserving SGD [19.273542515320372]
  Differentially-Private Gradient Descent (DP-SGD) prevents training-data privacy breaches by adding noise to the clipped gradient during SGD training. The same clipping operation and additive noise across training steps results in unstable updates and even a ramp-up period. We propose the dynamic DP-SGD, which has a lower privacy cost than the DP-SGD during updates until they achieve the same target privacy budget.
  arXiv  Detail & Related papers  (2021-10-30T04:45:11Z)
• Partial sensitivity analysis in differential privacy [58.730520380312676]
  We investigate the impact of each input feature on the individual's privacy loss. We experimentally evaluate our approach on queries over private databases. We also explore our findings in the context of neural network training on synthetic data.
  arXiv  Detail & Related papers  (2021-09-22T08:29:16Z)
• Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
  We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
  arXiv  Detail & Related papers  (2020-09-18T20:18:35Z)

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.