N-grams Bayesian Differential Privacy

• URL: http://arxiv.org/abs/2101.12736v1
• Date: Fri, 29 Jan 2021 18:48:49 GMT
• Title: N-grams Bayesian Differential Privacy
• Abstract summary: We propose a differential privacy mechanism that uses public data as a prior in a Bayesian setup to provide tighter bounds on the privacy loss metric epsilon. It achieves up to 85% reduction in KL divergence compared to previously known mechanisms at epsilon equals 0.1. We compare our mechanism to k-anonymity in a n-gram language modelling task and show that it offers competitive performance at large vocabulary sizes.
• Score: 1.3443690690260939
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Differential privacy has gained popularity in machine learning as a strong privacy guarantee, in contrast to privacy mitigation techniques such as k-anonymity. However, applying differential privacy to n-gram counts significantly degrades the utility of derived language models due to their large vocabularies. We propose a differential privacy mechanism that uses public data as a prior in a Bayesian setup to provide tighter bounds on the privacy loss metric epsilon, and thus better privacy-utility trade-offs. It first transforms the counts to log space, approximating the distribution of the public and private data as Gaussian. The posterior distribution is then evaluated and softmax is applied to produce a probability distribution. This technique achieves up to 85% reduction in KL divergence compared to previously known mechanisms at epsilon equals 0.1. We compare our mechanism to k-anonymity in a n-gram language modelling task and show that it offers competitive performance at large vocabulary sizes, while also providing superior privacy protection.

Related papers

• Differential Privacy for Symbolic Trajectories via the Permute-and-Flip Mechanism [42.73108425701334]
  We develop a new mechanism for privatizing state trajectories of symbolic systems that may be represented as words over a finite alphabet.<n>The accuracy of our mechanism is never worse than the prior state of the art, and we empirically show on a real traffic dataset that it introduces up to $55%$ less error.
  arXiv  Detail & Related papers  (2026-03-30T18:30:06Z)
• Differentially Private Random Feature Model [52.468511541184895]
  We produce a differentially private random feature model for privacy-preserving kernel machines. We show that our method preserves privacy and derive a generalization error bound for the method.
  arXiv  Detail & Related papers  (2024-12-06T05:31:08Z)
• Private Language Models via Truncated Laplacian Mechanism [18.77713904999236]
  We propose a novel private embedding method called the high dimensional truncated Laplacian mechanism. We show that our method has a lower variance compared to the previous private word embedding methods. Remarkably, even in the high privacy regime, our approach only incurs a slight decrease in utility compared to the non-private scenario.
  arXiv  Detail & Related papers  (2024-10-10T15:25:02Z)
• Enhanced Privacy Bound for Shuffle Model with Personalized Privacy [32.08637708405314]
  Differential Privacy (DP) is an enhanced privacy protocol which introduces an intermediate trusted server between local users and a central data curator. It significantly amplifies the central DP guarantee by anonymizing and shuffling the local randomized data. This work focuses on deriving the central privacy bound for a more practical setting where personalized local privacy is required by each user.
  arXiv  Detail & Related papers  (2024-07-25T16:11:56Z)
• Private prediction for large-scale synthetic text generation [28.488459921169905]
  We present an approach for generating differentially private synthetic text using large language models (LLMs) In the private prediction framework, we only require the output synthetic data to satisfy differential privacy guarantees.
  arXiv  Detail & Related papers  (2024-07-16T18:28:40Z)
• Optimal Private Discrete Distribution Estimation with One-bit Communication [63.413106413939836]
  We consider a private discrete distribution estimation problem with one-bit communication constraint. We characterize the first-orders of the worst-case trade-off under the one-bit communication constraint. These results demonstrate the optimal dependence of the privacy-utility trade-off under the one-bit communication constraint.
  arXiv  Detail & Related papers  (2023-10-17T05:21:19Z)
• Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy [51.11280118806893]
  We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. We study the local differential privacy guarantees of discrete-valued mechanisms with finite output space through the lens of $f$-differential privacy (DP) More specifically, we advance the existing literature by deriving tight $f$-DP guarantees for a variety of discrete-valued mechanisms.
  arXiv  Detail & Related papers  (2023-02-19T16:58:53Z)
• Smooth Anonymity for Sparse Graphs [69.1048938123063]
  differential privacy has emerged as the gold standard of privacy, however, when it comes to sharing sparse datasets. In this work, we consider a variation of $k$-anonymity, which we call smooth-$k$-anonymity, and design simple large-scale algorithms that efficiently provide smooth-$k$-anonymity.
  arXiv  Detail & Related papers  (2022-07-13T17:09:25Z)
• Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent [69.14164921515949]
  We characterize privacy guarantees for individual examples when releasing models trained by DP-SGD. We find that most examples enjoy stronger privacy guarantees than the worst-case bound. This implies groups that are underserved in terms of model utility simultaneously experience weaker privacy guarantees.
  arXiv  Detail & Related papers  (2022-06-06T13:49:37Z)
• Mixed Differential Privacy in Computer Vision [133.68363478737058]
  AdaMix is an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset.
  arXiv  Detail & Related papers  (2022-03-22T06:15:43Z)
• Distribution-Invariant Differential Privacy [4.700764053354502]
  We develop a distribution-invariant privatization (DIP) method to reconcile high statistical accuracy and strict differential privacy. Under the same strictness of privacy protection, DIP achieves superior statistical accuracy in two simulations and on three real-world benchmarks.
  arXiv  Detail & Related papers  (2021-11-08T22:26:50Z)
• 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)

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.