A new privacy accountant for Gaussian differential privacy measures individual privacy losses.
problem Bounding differential privacy loss for each participant in data analysis.
method Developed a privacy accountant for adaptive compositions of randomised mechanisms using Gaussian differential privacy.
result Provided optimal bounds for the Gaussian mechanism and constructed an approximative individual privacy accountant.
A new method for tighter privacy loss accounting in adaptive analyses.
problem Ensuring individual privacy in adaptive analyses while staying within a privacy budget.
method A personalized privacy loss estimate and a Rényi differential privacy filter.
result Personalized privacy loss accounting can be practical and tighter than existing methods.
Edgeworth Accountant calculates privacy loss under differential privacy compositions efficiently.
problem Efficiently computing overall privacy loss under composition of private algorithms.
method Analytical approach using f-differential privacy framework and Edgeworth expansion. result Non-asymptotic (ε,δ)-differential privacy bounds with reduced computational cost. This paper improves privacy accounting in decentralized FL using f-Differential Privacy.
problem Challenges in accurately quantifying privacy budget in decentralized FL.
method Develops two new f-DP-based accounting methods for decentralized FL.
result Yields tighter (ε,δ) bounds and improved utility compared to existing methods.
The paper improves privacy accounting for discrete-valued mechanisms and the subsampled Gaussian mechanism.
problem Improving the accuracy and efficiency of differential privacy accounting for discrete outputs.
method Uses fast Fourier transform (FFT) for rigorous error analysis and accounting of privacy loss.
result Provides strict lower and upper bounds for (ε,δ)-values, demonstrating up to 75% reduction in noise variance. Traditional differential privacy is independent of the data distribution. However, this is not well-matched with the modern machine learning context, where models are trained on specific data. As a result, achieving meaningful privacy guarantees in ML often excessively reduces accuracy. We propose Bayesian differential…
Unified framework for subsampling mechanisms with tighter privacy guarantees.
problem Improving privacy in machine learning models through subsampling.
method Conditional optimal transport for deriving mechanism-specific subsampling guarantees.
result Tighter privacy bounds for subsampled mechanisms compared to traditional methods.
New insights into privacy guarantees for subsampled mechanisms under composition.
problem Tight privacy guarantees for the composition of subsampled differentially private mechanisms.
method Addressed confusion points in privacy accounting for subsampled mechanisms, providing examples and counterexamples.
result Privacy guarantees for subsampled mechanisms differ significantly between Poisson subsampling and sampling without replacement.
Big data transforms accounting and auditing, enhancing insights but posing challenges.
problem Challenges in data privacy and security with increased data sources.
method Utilizing AI and machine learning for efficient data analysis and anomaly detection.
result Enhanced analytics tools and continuous learning are key to overcoming challenges.
Paper extends FFT-based differential privacy method to heterogeneous compositions.
problem Computing accurate differential privacy guarantees for mixed mechanisms.
method Uses Fast Fourier Transform (FFT) for error analysis and parameter selection.
result Provides tighter bounds for heterogeneous compositions compared to homogeneous cases.
BlockFLow ensures privacy and accountability in federated learning.
problem Malicious agents can weaken federated learning models.
method Differential privacy, auditing mechanism, Ethereum smart contracts.
result Audit scores reflect the quality of honest agents' datasets.
The workshop focuses on AI principles for structured data.
problem Using AI on structured data for decision-making.
method Addressing principles of privacy, accountability, interpretability, robustness, and reasoning.
result Designing approaches to use structured data for reliable decisions.
Efficiently calculates privacy guarantees for 2020 Census data.
problem Evaluate privacy guarantees for 2020 U.S. Census data releases.
method Sieve-accelerated quadrature method to evaluate tail probabilities of high-dimensional convolutions.
result Achieves 1,824-fold speedup over prior methods while maintaining error tolerances.
Constructs models to meet any DP requirement without retraining.
problem Evolving privacy requirements at inference time.
method Two post-processing techniques: random selection and linear combination.
result Final private models satisfying any target privacy parameter.
Gaussian DP improves reporting of ML algorithms' differential privacy guarantees.
problem Incomplete and misleading DP guarantees for ML algorithms.
method Using non-asymptotic Gaussian Differential Privacy (GDP) to provide accurate bounds on privacy profiles of ML algorithms.
result GDP captures the entire privacy profile of DP-SGD and related algorithms with virtually no error.
DP-SGD provides privacy guarantees for all data points, but we propose output-specific DP to better account for individual examples.
problem Accounting for individual privacy guarantees in DP-SGD.
method Output-specific (ε,δ)-DP and an efficient algorithm to investigate individual privacy across datasets. result Most examples enjoy stronger privacy guarantees than the worst-case bound, and there is a correlation between training loss and privacy parameter.
Paper relaxes differential privacy for correlated features, improving privacy-utility trade-off.
problem Standard differential privacy ignores feature correlation, leading to suboptimal privacy-utility balance.
method Introduces CorrDP framework that accounts for feature correlation, using total variation distance for quantification.
result CorrDP algorithms outperform standard DP in synthetic and real-world datasets with insensitive features.
We study the problem of subsampling in differential privacy (DP), a question that is the centerpiece behind many successful differentially private machine learning algorithms. Specifically, we provide a tight upper bound on the Rényi Differential Privacy (RDP) (Mironov, 2017) parameters for algorithms that: (1) subsamp…
Paper improves privacy bounds for shuffle model using novel numerical techniques.
problem Improving privacy guarantees in the shuffle model of differential privacy.
method Develops and evaluates numerical techniques for tighter (ε,δ)-differential privacy bounds. result Accurately evaluates privacy loss distribution for adaptive compositions of shufflers.
This paper quantifies privacy loss in exploratory data analysis.
problem Privacy loss in exploratory data analysis is often overlooked in privacy budgets.
method Quantitative analysis of privacy loss for statistical functions.
result Privacy loss must be considered in calculating machine learning privacy budgets.
We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy loss bounds. We adapt the Bayesian privacy accounting method to the federated sett…
We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of Rényi differential privacy (RDP). Our result is based on the joint range of two f-divergences that underlie the approximate and the Rényi variations of differential privacy. We apply our result to the moments acc…
Differentially private (DP) machine learning has recently become popular. The privacy loss of DP algorithms is commonly reported using (ε,δ)-DP. In this paper, we propose a numerical accountant for evaluating the privacy loss for algorithms with continuous one dimensional output. This accountant can be appl…
Companies increasingly expose machine learning (ML) models trained over sensitive user data to untrusted domains, such as end-user devices and wide-access model stores. We present Sage, a differentially private (DP) ML platform that bounds the cumulative leakage of training data through models. Sage builds upon the ric…
New sampling scheme improves privacy in DP-SGD without sacrificing utility.
problem Suboptimal privacy amplification due to participation variance in Poisson subsampling.
method Balanced Iteration Subsampling (BIS) with structured randomness.
result BIS achieves stronger privacy amplification than Poisson subsampling and is optimal at both extremes of noise spectrum.
New method improves privacy risk evaluation of machine learning models.
problem Machine learning models can be vulnerable to membership inference attacks.
method Proposed new inference attack method based on prediction entropy, and introduced privacy risk score metric.
result Existing defense approaches are not as effective as previously reported.
Expands differential privacy mechanisms to include the Generalized Gaussian mechanism for improved private machine learning.
problem Improving privacy in machine learning algorithms while maintaining utility.
method Introduces and analyzes the Generalized Gaussian (GG) mechanism for differential privacy.
result The GG mechanism provides better performance than the Laplace and Gaussian mechanisms across various values of β.
Framework evaluates privacy cost of non-private pre-processing in DP pipelines.
problem Privacy cost of non-private data-dependent pre-processing in DP machine learning pipelines.
method Establishes upper bounds on overall privacy guarantees using Smooth DP and bounded sensitivity.
result Explicit overall privacy guarantees for various pre-processing algorithms.
This guide simplifies applying differential privacy to machine learning models.
problem Limited practical guidance for achieving good privacy-utility-computations in ML models.
method Comprehensive self-contained guide covering theory and practical implementation.
result Achieves best possible DP ML model with rigorous privacy guarantees.
Paper tackles federated learning with privacy, enhancing target data analysis.
problem Heterogeneity and privacy of distributed data in federated learning.
method Formulates federated differential privacy, studies statistical problems under privacy constraints.
result Federated differential privacy offers a balance between privacy and knowledge transfer.
Proactive DP optimizes privacy and utility in DP-SGD with a fixed privacy budget.
problem Balancing privacy and utility in differential privacy for machine learning.
method Proposes a pro-active DP framework that allows a-priori selection of DP-SGD parameters to maximize test accuracy.
result Proactive DP can optimize utility of DP-SGD with a fixed privacy budget (ε, δ).
Noise-aware Bayesian inference framework for locally private data collection.
problem Privacy-preserving data collection with non-trustworthy aggregators.
method Noise-aware probabilistic modeling framework for Bayesian inference under LDP.
result Demonstrated efficacy in parameter estimation for various distributions and regression models.
New algorithm maintains privacy while improving model performance in selective release.
problem Privacy degradation and slow convergence in DPSGD.
method Differentially Private Selective Release based on Clipped Gradients (DPSR-CG).
result Maintains strict privacy guarantees while achieving exceptional model performance.
A new federated learning framework with sparsification and adaptive optimization for privacy and efficiency.
problem Lack of sufficient privacy protection in federated learning.
method Integrates random sparsification with gradient perturbation and acceleration techniques to enhance privacy and efficiency.
result Outperforms previous differentially-private federated learning approaches in privacy and efficiency.
Paper improves differential privacy analysis for machine learning.
problem Quantifying privacy leakage in noisy gradient descent.
method Shifted interpolation in f-differential privacy. result First exact privacy analysis for strongly convex optimization.
Gaussian processes with differential privacy protect both inputs and outputs.
problem Previous DP methods only protected model outputs, not inputs.
method Sparse GP with private variational approximation, adjusting covariance for DP noise.
result Accurate models can be produced under strong privacy protection with sufficient data.
Enhanced privacy, utility, and efficiency through MUST subsampling.
problem Balancing privacy, utility, and computational efficiency in data analysis.
method MUltistage Sampling Technique (MUST) for privacy amplification in differential privacy.
result MUST offers stronger privacy guarantees (ϵ) than one-stage subsampling methods while maintaining similar utility and computational efficiency. In this work we address the practical challenges of training machine learning models on privacy-sensitive datasets by introducing a modular approach that minimizes changes to training algorithms, provides a variety of configuration strategies for the privacy mechanism, and then isolates and simplifies the critical logi…
Generative Adversarial Networks (GANs) are one of the well-known models to generate synthetic data including images, especially for research communities that cannot use original sensitive datasets because they are not publicly accessible. One of the main challenges in this area is to preserve the privacy of individuals…
Balls-and-Bins sampling improves DP-SGD privacy and utility.
problem Improving privacy and utility in DP-SGD implementations.
method Introducing Balls-and-Bins sampling as an alternative to shuffling in DP-SGD.
result Balls-and-Bins sampling achieves utility comparable to shuffling while offering better privacy amplification.
It is often the case that, within an online recommender system, multiple users share a common account. Can such shared accounts be identified solely on the basis of the userprovided ratings? Once a shared account is identified, can the different users sharing it be identified as well? Whenever such user identification …
New privacy bounds for DP-SGD's last iterate, even with cyclic sampling.
problem Privacy of the last iterate in DP-SGD with cyclic sampling.
method Established new RDP upper bounds for the last iterate under realistic assumptions.
result Privacy bounds for DP-SGD's last iterate with cyclic sampling and clipping, even for nonconvex losses.
Study on protecting sensitive properties of datasets during analysis.
problem Ensuring privacy of sensitive properties in datasets.
method Proposes definitions and mechanisms for attribute privacy using the Pufferfish framework.
result Developed efficient and inefficient mechanisms for attribute privacy.
This paper improves privacy bounds for DP algorithms using f-DP.
problem Difficulty in analyzing randomness in DP algorithms due to mixture distributions.
method Derives a closed-form expression for trade-off functions and analyzes f-DP. result Enhances privacy of DP-GD with random initialization and shuffling models.
Proposes a text perturbation method using a Mahalanobis metric to balance privacy and utility.
problem Low utility of text analysis when using spherical noise for privacy-preserving text embedding.
method Regularized Mahalanobis metric to add elliptical noise, accounting for embedding space density.
result Improves privacy statistics while maintaining utility, outperforming Laplace mechanism.
Three DP variants linked, improving SGD privacy bounds.
problem Relating different DP variants for tighter privacy bounds.
method Developed machinery to relate approximate DP to RDP and hypothesis test DP.
result Improved privacy guarantees for noisy SGD.
Decor protects decentralized learning models from curious users.
problem Privacy violation in decentralized learning.
method Decor uses correlated Gaussian noises to protect local models in decentralized SGD with differential privacy guarantees.
result Decor matches central DP optimal privacy-utility trade-off for arbitrary connected graphs.
We develop a privatised stochastic variational inference method for Latent Dirichlet Allocation (LDA). The iterative nature of stochastic variational inference presents challenges: multiple iterations are required to obtain accurate posterior distributions, yet each iteration increases the amount of noise that must be …