Practitioners' Perspectives on a Differential Privacy Deployment Registry

• URL: http://arxiv.org/abs/2509.13509v1
• Date: Tue, 16 Sep 2025 20:15:15 GMT
• Title: Practitioners' Perspectives on a Differential Privacy Deployment Registry
• Authors: Priyanka Nanayakkara, Elena Ghazi, Salil Vadhan,
• Abstract summary: Differential privacy (DP) is a principled approach to producing statistical data products with strong, mathematically provable privacy guarantees.<n>Dwork, Kohli, and Mulligan proposed a public-facing registry ("registry") of DP deployments.<n>We conduct a study with 21 real-world DP deployments to understand how practitioners would use the registry.
• Score: 0.8105516788827453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Differential privacy (DP) -- a principled approach to producing statistical data products with strong, mathematically provable privacy guarantees for the individuals in the underlying dataset -- has seen substantial adoption in practice over the past decade. Applying DP requires making several implementation decisions, each with significant impacts on data privacy and/or utility. Hence, to promote shared learning and accountability around DP deployments, Dwork, Kohli, and Mulligan (2019) proposed a public-facing repository ("registry") of DP deployments. The DP community has recently started to work toward realizing this vision. We contribute to this effort by (1) developing a holistic, hierarchical schema to describe any given DP deployment and (2) designing and implementing an interactive interface to act as a registry where practitioners can access information about past DP deployments. We (3) populate our interface with 21 real-world DP deployments and (4) conduct an exploratory user study with DP practitioners ($n=16$) to understand how they would use the registry, as well as what challenges and opportunities they foresee around its adoption. We find that participants were enthusiastic about the registry as a valuable resource for evaluating prior deployments and making future deployments. They also identified several opportunities for the registry, including that it can become a "hub" for the community and support broader communication around DP (e.g., to legal teams). At the same time, they identified challenges around the registry gaining adoption, including the effort and risk involved with making implementation choices public and moderating the quality of entries. Based on our findings, we offer recommendations for encouraging adoption and increasing the registry's value not only to DP practitioners, but also to policymakers, data users, and data subjects.

Related papers

• Advancing privacy in learning analytics using differential privacy [0.412484724941528]
  This paper addresses the challenge of balancing learner data privacy with the use of data in learning analytics (LA) by proposing a novel framework by applying Differential Privacy (DP)<n>We introduce the first DP framework specifically designed for LA and provide practical guidance for its implementation.<n>We demonstrate the use of this framework through a LA usage scenario and validate DP in safeguarding data privacy against potential attacks through an experiment on a well-known LA dataset.
  arXiv  Detail & Related papers  (2025-01-03T12:36:11Z)
• SoK: Usability Studies in Differential Privacy [3.2703125808871247]
  Differential Privacy (DP) has emerged as a pivotal approach for safeguarding individual privacy in data analysis.<n>This paper presents a comprehensive systematization of existing research studies around the usability of DP.
  arXiv  Detail & Related papers  (2024-12-22T02:21:57Z)
• 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)
• Incentives in Private Collaborative Machine Learning [56.84263918489519]
  Collaborative machine learning involves training models on data from multiple parties. We introduce differential privacy (DP) as an incentive. We empirically demonstrate the effectiveness and practicality of our approach on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-04-02T06:28:22Z)
• 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)
• Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning [66.20311762506702]
  dataset pruning (DP) has emerged as an effective way to improve data efficiency. We propose two new DP methods, label mapping and feature mapping, for supervised and self-supervised pretraining settings. We show that source data classes can be pruned by up to 40% 80% without sacrificing downstream performance.
  arXiv  Detail & Related papers  (2023-10-13T00:07:49Z)
• A Unified View of Differentially Private Deep Generative Modeling [60.72161965018005]
  Data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released.
  arXiv  Detail & Related papers  (2023-09-27T14:38:16Z)
• Evaluating the Usability of Differential Privacy Tools with Data Practitioners [4.072285093323275]
  Differential privacy (DP) has become the gold standard in privacy-preserving data analytics, but implementing it in real-world datasets and systems remains challenging. Recently developed DP tools aim to make DP implementation easier, but limited research has investigated these DP tools' usability. We evaluated the usability of four Python-based open-source DP tools: DiffPrivLib, Tumult Analytics, PipelineDP, and OpenDP.
  arXiv  Detail & Related papers  (2023-09-24T00:10:47Z)
• ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy [19.017342515321918]
  Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. We present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single user's data may belong to multiple silos.
  arXiv  Detail & Related papers  (2023-08-23T15:50:51Z)
• Exploring the Benefits of Visual Prompting in Differential Privacy [54.56619360046841]
  Visual Prompting (VP) is an emerging and powerful technique that allows sample-efficient adaptation to downstream tasks by engineering a well-trained frozen source model. We explore and integrate VP into canonical DP training methods and demonstrate its simplicity and efficiency.
  arXiv  Detail & Related papers  (2023-03-22T01:01:14Z)
• How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy [22.906644117887133]
  Differential Privacy (DP) has become a gold standard for making formal statements about data anonymization. The adoption of DP is hindered by limited practical guidance of what DP protection entails, what privacy guarantees to aim for, and the difficulty of achieving good privacy-utility-computation trade-offs for ML models. This work is a self-contained guide that gives an in-depth overview of the field of DP ML and presents information about achieving the best possible DP ML model with rigorous privacy guarantees.
  arXiv  Detail & Related papers  (2023-03-01T16:56:39Z)

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.