On the Inherent Privacy Properties of Discrete Denoising Diffusion Models

• URL: http://arxiv.org/abs/2310.15524v3
• Date: Mon, 3 Jun 2024 03:02:54 GMT
• Title: On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
• Authors: Rongzhe Wei, Eleonora Kreačić, Haoyu Wang, Haoteng Yin, Eli Chien, Vamsi K. Potluru, Pan Li,
• Abstract summary: We present the pioneering theoretical exploration of the privacy preservation inherent in discrete diffusion models. Our framework elucidates the potential privacy leakage for each data point in a given training dataset. Our bounds also show that training with $s$-sized data points leads to a surge in privacy leakage.
• Score: 17.773335593043004
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Privacy concerns have led to a surge in the creation of synthetic datasets, with diffusion models emerging as a promising avenue. Although prior studies have performed empirical evaluations on these models, there has been a gap in providing a mathematical characterization of their privacy-preserving capabilities. To address this, we present the pioneering theoretical exploration of the privacy preservation inherent in discrete diffusion models (DDMs) for discrete dataset generation. Focusing on per-instance differential privacy (pDP), our framework elucidates the potential privacy leakage for each data point in a given training dataset, offering insights into how the privacy loss of each point correlates with the dataset's distribution. Our bounds also show that training with $s$-sized data points leads to a surge in privacy leakage from $(\epsilon, O(\frac{1}{s^2\epsilon}))$-pDP to $(\epsilon, O(\frac{1}{s\epsilon}))$-pDP of the DDM during the transition from the pure noise to the synthetic clean data phase, and a faster decay in diffusion coefficients amplifies the privacy guarantee. Finally, we empirically verify our theoretical findings on both synthetic and real-world datasets.

Related papers

• Differentially Private Non Parametric Copulas: Generating synthetic data with non parametric copulas under privacy guarantees [0.0]
  This work focuses on enhancing a non-parametric co-pula-based synthetic data generation model, DPNPC, by incorporating Differential Privacy. We compare DPNPC with three other models (PrivBayes, DP-Copula, and DP-Histogram) across three public datasets, evaluating privacy, utility, and execution time.
  arXiv  Detail & Related papers  (2024-09-27T10:18:14Z)
• Quantifying and Mitigating Privacy Risks for Tabular Generative Models [13.153278585144355]
  Synthetic data from generative models emerges as the privacy-preserving data-sharing solution. We propose DP-TLDM, Differentially Private Tabular Latent Diffusion Model. We show that DP-TLDM improves the synthetic quality by an average of 35% in data resemblance, 15% in the utility for downstream tasks, and 50% in data discriminability.
  arXiv  Detail & Related papers  (2024-03-12T17:27:49Z)
• FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning [54.26614091429253]
  Federated instruction tuning (FedIT) is a promising solution, by consolidating collaborative training across multiple data owners. FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks. We propose FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning.
  arXiv  Detail & Related papers  (2024-03-10T08:41:22Z)
• Towards Theoretical Understandings of Self-Consuming Generative Models [56.84592466204185]
  This paper tackles the emerging challenge of training generative models within a self-consuming loop. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models. We present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.
  arXiv  Detail & Related papers  (2024-02-19T02:08:09Z)
• 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)
• Differentially Private Synthetic Data Using KD-Trees [11.96971298978997]
  We exploit space partitioning techniques together with noise perturbation and thus achieve intuitive and transparent algorithms. We propose both data independent and data dependent algorithms for $epsilon$-differentially private synthetic data generation. We show empirical utility improvements over the prior work, and discuss performance of our algorithm on a downstream classification task on a real dataset.
  arXiv  Detail & Related papers  (2023-06-19T17:08:32Z)
• Private Set Generation with Discriminative Information [63.851085173614]
  Differentially private data generation is a promising solution to the data privacy challenge. Existing private generative models are struggling with the utility of synthetic samples. We introduce a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-07T10:02:55Z)
• DP2-Pub: Differentially Private High-Dimensional Data Publication with Invariant Post Randomization [58.155151571362914]
  We propose a differentially private high-dimensional data publication mechanism (DP2-Pub) that runs in two phases. splitting attributes into several low-dimensional clusters with high intra-cluster cohesion and low inter-cluster coupling helps obtain a reasonable privacy budget. We also extend our DP2-Pub mechanism to the scenario with a semi-honest server which satisfies local differential privacy.
  arXiv  Detail & Related papers  (2022-08-24T17:52:43Z)
• PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning [1.8692254863855962]
  We propose a new framework of data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion. Our proposal has theoretical guarantees of performance, and empirical evaluations on multiple datasets show that our approach outperforms other methods at reasonable levels of privacy.
  arXiv  Detail & Related papers  (2021-06-08T18:00:01Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)
• Privacy-Preserving Adversarial Network (PPAN) for Continuous non-Gaussian Attributes [6.657723602564176]
  A privacy-preserving adversarial network (PPAN) was recently proposed to address the issue of privacy in data sharing. In this study, we evaluate the PPAN model for continuous non-Gaussian data where lower and upper bounds of the privacy-preserving problem are used.
  arXiv  Detail & Related papers  (2020-03-11T15:29:35Z)

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.