Considerations on the Theory of Training Models with Differential Privacy

• URL: http://arxiv.org/abs/2303.04676v2
• Date: Sun, 16 Jul 2023 20:13:28 GMT
• Title: Considerations on the Theory of Training Models with Differential Privacy
• Authors: Marten van Dijk and Phuong Ha Nguyen
• Abstract summary: In federated learning collaborative learning takes place by a set of clients who each want to remain in control of how their local training data is used. Differential privacy is one method to limit privacy leakage.
• Score: 13.782477759025344
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: In federated learning collaborative learning takes place by a set of clients who each want to remain in control of how their local training data is used, in particular, how can each client's local training data remain private? Differential privacy is one method to limit privacy leakage. We provide a general overview of its framework and provable properties, adopt the more recent hypothesis based definition called Gaussian DP or $f$-DP, and discuss Differentially Private Stochastic Gradient Descent (DP-SGD). We stay at a meta level and attempt intuitive explanations and insights \textit{in this book chapter}.

Related papers

• Beyond the Mean: Differentially Private Prototypes for Private Transfer Learning [16.028575596905554]
  We propose Differentially Private Prototype Learning (DPPL) as a new paradigm for private transfer learning. DPPL generates prototypes that represent each private class in the embedding space and can be publicly released for inference. We show that privacy-utility trade-offs can be further improved when leveraging the public data beyond pre-training of the encoder.
  arXiv  Detail & Related papers  (2024-06-12T09:41:12Z)
• LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification [67.92145284679623]
  We propose a DP-based tutor that models the noised private distribution and controls samples' generation with a low privacy cost. We theoretically analyze our model's privacy protection and empirically verify our model.
  arXiv  Detail & Related papers  (2024-02-26T11:52:55Z)
• Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks [72.51255282371805]
  We prove a privacy bound for the KL divergence between model distributions on worst-case neighboring datasets. We find that this KL privacy bound is largely determined by the expected squared gradient norm relative to model parameters during training.
  arXiv  Detail & Related papers  (2023-10-31T16:13:22Z)
• Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond [6.731000738818571]
  Federated learning (FL) is a framework for training machine learning models in a distributed and collaborative manner. In this paper, we address the triadic interaction among personalization, privacy guarantees, and fairness attained by models trained within the FL framework. A method is put forth that introduces group privacy assurances through the utilization of $d$-privacy.
  arXiv  Detail & Related papers  (2023-09-01T12:20:19Z)
• Independent Distribution Regularization for Private Graph Embedding [55.24441467292359]
  Graph embeddings are susceptible to attribute inference attacks, which allow attackers to infer private node attributes from the learned graph embeddings. To address these concerns, privacy-preserving graph embedding methods have emerged. We propose a novel approach called Private Variational Graph AutoEncoders (PVGAE) with the aid of independent distribution penalty as a regularization term.
  arXiv  Detail & Related papers  (2023-08-16T13:32:43Z)
• Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile [23.05994842923702]
  We study a privacy metric that quantifies the extent to which a model trained on a dataset using a Differential Privacy mechanism is covered" by each of the distributions resulting from training on neighboring datasets. We show that the privacy profile can be used to probe an observed transition to indistinguishability that takes place in the neighboring distributions as $epsilon$ decreases.
  arXiv  Detail & Related papers  (2023-06-27T20:39:07Z)
• Personalized PATE: Differential Privacy for Machine Learning with Individual Privacy Guarantees [1.2691047660244335]
  We propose three novel methods to support training an ML model with different personalized privacy guarantees within the training data. Our experiments show that our personalized privacy methods yield higher accuracy models than the non-personalized baseline.
  arXiv  Detail & Related papers  (2022-02-21T20:16:27Z)
• Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization [57.98426940386627]
  We show that coordinating local learning with private centralized learning yields a generically useful and improved tradeoff between accuracy and privacy. We illustrate our theoretical results with experiments on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-02-10T20:44:44Z)
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence [73.14373832423156]
  We propose DP-Sinkhorn, a novel optimal transport-based generative method for learning data distributions from private data with differential privacy. Unlike existing approaches for training differentially private generative models, we do not rely on adversarial objectives.
  arXiv  Detail & Related papers  (2021-11-01T18:10:21Z)
• Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy [67.4471689755097]
  This paper empirically demonstrates that the clipped FedAvg can perform surprisingly well even with substantial data heterogeneity. We provide the convergence analysis of a differential private (DP) FedAvg algorithm and highlight the relationship between clipping bias and the distribution of the clients' updates.
  arXiv  Detail & Related papers  (2021-06-25T14:47:19Z)
• Federated $f$-Differential Privacy [19.499120576896228]
  Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information. We introduce federated $f$-differential privacy, a new notion specifically tailored to the federated setting. We then propose a generic private federated learning framework PriFedSync that accommodates a large family of state-of-the-art FL algorithms.
  arXiv  Detail & Related papers  (2021-02-22T16:28:21Z)

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.