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.
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.
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.
Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, ε, about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of ε in order to get acceptable utility of …
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.
New bounds for LDP with heterogeneous privacy levels guaranteeing high probability of accuracy.
problem Statistical estimation under LDP with users having varying privacy levels.
method Developed finite sample upper bounds in ℓ_2-norm with high probability, complemented by lower bounds.
result Optimal guarantees for heterogeneous LDP in terms of probability and constants.
The paper provides privacy guarantees for MCMC algorithms using Langevin dynamics.
problem Ensuring differential privacy in MCMC algorithms.
method Novel methodology combining Girsanov's theorem and perturbation trick.
result Established (Rényi) DP guarantees for Langevin algorithms.
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…
Improves privacy guarantees by analyzing randomness in privacy-preserving mechanisms.
problem Balancing user privacy and business constraints in privacy-preserving mechanisms.
method Analyzes explicit and implicit randomness in privacy mechanisms and proposes a probabilistic calibration method.
result Proposes privacy at risk, providing stronger privacy guarantees with quantifiable risks.
Proposes MIP, a privacy notion that requires less randomness than DP, leading to better utility.
problem Preserving privacy in machine learning models with sensitive data.
method Introduces membership inference privacy (MIP) as a new privacy notion and shows its relationship with differential privacy (DP).
result MIP can be achieved with less randomness than DP, resulting in better utility.
Thompson Sampling remains differentially private with minimal modifications.
problem Ensuring privacy in Thompson Sampling for multi-arm bandits.
method Demonstrated differential privacy of original Thompson Sampling, provided per-round guarantees, and introduced modifications for tighter privacy.
result Privacy guarantees can be tuned by modifying the algorithm, and these modifications impact expected regret.
Communication and privacy are two critical concerns in distributed learning. Many existing works treat these concerns separately. In this work, we argue that a natural connection exists between methods for communication reduction and privacy preservation in the context of distributed machine learning. In particular, we…
Improved shuffling technique amplifies privacy guarantees for anonymous data contributions.
problem Enhancing privacy in systems where data is contributed anonymously.
method Developed a new approach to random shuffling that amplifies differential privacy guarantees.
result Achieved asymptotically optimal privacy amplification with nearly optimal dependence in ε.
Paper proves privacy guarantees for shuffled and online PNSGD, reducing noise over time.
problem Privacy amplification in shuffled and online PNSGD settings.
method Iterative analysis of PNSGD with hidden updates, proving privacy guarantees for shuffled and online settings.
result Privacy guarantees for shuffled and online PNSGD with reduced noise over time.
Privacy is enhanced by synthetic data release even with unlimited data.
problem Improving privacy guarantees for synthetic data release.
method Analyzing a bounded-parameter assumption to show privacy amplification persists with unlimited synthetic records.
result Privacy amplification is possible even with an unbounded number of synthetic records.
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.
Enhanced stability improves privacy in machine learning.
problem Improving privacy in machine learning training while maintaining accuracy.
method Study of stability in private empirical risk minimization, focusing on strongly-convex loss functions and uniform stability.
result An algorithm with uniform stability of β implies a bound of O(√β) on the scale of noise required for differential privacy.
This paper benchmarks privacy-preserving machine learning on medical images.
problem Ensuring privacy in medical image analysis while maintaining model accuracy.
method Comparing Local-DP and DP-SGD for differential privacy in medical imagery.
result Theoretical privacy guarantees do not fully align with real-world performance.
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.
Private RL algorithm with privacy guarantees for personalized medicine decisions.
problem Privacy-preserving reinforcement learning for personalized medicine decisions.
method Developed a private optimism-based RL algorithm using joint differential privacy (JDP).
result Achieved strong PAC and regret bounds with a privacy guarantee.
New framework provides privacy guarantees for practical federated learning.
problem Inadequate privacy guarantees for federated learning due to restrictive assumptions.
method Fed-α-NormEC, integrating multiple local updates, partial client participation, and standard assumptions. result Provably convergent and differentially private federated learning framework.
While many solutions for privacy-preserving convex empirical risk minimization (ERM) have been developed, privacy-preserving nonconvex ERM remains a challenge. We study nonconvex ERM, which takes the form of minimizing a finite-sum of nonconvex loss functions over a training set. We propose a new differentially private…
Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presents a formal approach to carrying out privacy preserving text perturbation using the notion of dx-privacy designed to achieve geo-indistingui…
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.
Improves privacy amplification by shuffling for differential privacy.
problem Enhancing privacy guarantees in systems with anonymous data contributions.
method Theoretical and numerical analysis of Rényi differential privacy parameters and privacy amplification by shuffling.
result First asymptotically optimal analysis of Rényi differential privacy parameters for shuffled outputs.
New federated f-differential privacy for collaborative learning.
problem Privacy in federated learning.
method Introducing federated f-differential privacy and proposing a generic private federated learning framework. result Proves federated f-differential privacy provides privacy guarantee on each record of one client's data. Paper improves privacy for language models against reconstruction attacks.
problem Reconstruction attacks can regenerate training data from language models.
method Uses Rényi differential privacy with optimized privacy budgets.
result Better privacy guarantees for extraction of rare secrets.
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…
New federated learning protocols resist Byzantine failures and offer privacy guarantees.
problem Resisting Byzantine failures in federated learning.
method Proposes robust federated learning protocols with optimal statistical rates and privacy guarantees.
result Achieves nearly optimal statistical rates and tight rate in terms of all parameters for strongly convex losses.
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 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.
DP-REC combines privacy and communication efficiency in federated learning.
problem Combining privacy and communication efficiency in federated learning.
method DP-REC uses Relative Entropy Coding (REC) for compression and a minor modification for differential privacy.
result DP-REC reduces communication costs while maintaining privacy comparable to state-of-the-art methods.
NAPP-ERM improves ERM with differential privacy guarantees by iteratively achieving target regularization and delivering strong convexity.
problem Over-regularization in privacy-preserving ERM approaches.
method Noise-Augmented Privacy-Preserving Empirical Risk Minimization (NAPP-ERM) with a dual-purpose l2 regularizer and privacy budget retrieval strategy.
result Mitigates over-regularization and achieves strong convexity through a single regularizer.
Differentially private fair binary classification algorithm developed.
problem Balancing privacy and fairness in binary classification.
method Decoupling technique for fairness, refinement for differential privacy.
result Algorithm maintains fairness, privacy, and utility guarantees.
FLORAS uses orthogonal sequences for SISO FL, offering both DP and convergence guarantees.
problem Privacy-preserving wireless federated learning in SISO systems.
method Leverages orthogonal sequences to eliminate CSIT requirement and provide DP guarantees.
result FLORAS achieves a smooth tradeoff between convergence rate and DP levels.
2020 Census uses more noise to protect privacy than needed, improving data accuracy.
problem Ensuring privacy in census data while maintaining accuracy for policy decisions.
method Applied f-differential privacy to track and reduce noise across geographical levels. result The 2020 Census provides stronger privacy protections than its nominal guarantees suggest.
LDP is equivalent to contraction of E_γ-divergence, impacting privacy and utility.
problem Analyzing trade-offs between privacy and utility in estimation problems.
method Equivalence of LDP constraints to contraction coefficients of E_γ-divergence, using f-divergences and estimation-theoretic tools.
result LDP guarantees can be expressed in terms of contraction coefficients of arbitrary f-divergences.
New method compares DP mechanisms beyond (ε,δ) pairs.
problem Current DP mechanism comparisons overlook substantial differences.
method Introduces Δ-divergence for robust comparison. result Demonstrates gaps in current DP-SGD practices.
Enhances privacy in data annotation and inspection with synthetic data.
problem Improving privacy in machine learning tasks like data annotation and inspection.
method Employing Bayesian differential privacy to generate higher-fidelity synthetic data.
result Produces higher-fidelity samples, detecting more subtle data errors and biases.
This paper improves deep learning models' accuracy with differential privacy using gradient encoding and denoising.
problem Deep learning models leak sensitive information about their training datasets.
method Gradient encoding to map gradients to a smaller vector space, and denoising for post-processing.
result Our technique achieves better model accuracy with differential privacy guarantees compared to state-of-the-art methods.
We study the problem of data release with privacy, where data is made available with privacy guarantees while keeping the usability of the data as high as possible --- this is important in health-care and other domains with sensitive data. In particular, we propose a method of masking the private data with privacy guar…
DPNR preserves privacy of text representations using differential privacy.
problem Privacy leakage in deep learning text representations.
method DPNR uses Differential Privacy to provide formal privacy guarantees and dropout masking for enhanced privacy.
result DPNR reduces privacy leakage without significantly sacrificing main task performance.
Combining differential privacy and federated learning improves data security.
problem Ensuring privacy in distributed machine learning.
method Integrating differential privacy with federated learning protocols.
result Achieved comparable prediction accuracy to non-distributed learning while maintaining strict privacy.
Structured subsampling improves privacy in deep time series forecasting.
problem Incompatible privacy guarantees with time series forecasting.
method Structured subsampling of sequential data for privacy amplification.
result Structured subsampling enables training with strong privacy guarantees.
Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak sensitive features. To identify such privacy violations, existing model auditin…
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.
Offline RL algorithms protect privacy while learning from sensitive data.
problem Learning sensitive data in financial, legal, and healthcare applications.
method Differential privacy guarantees for offline RL algorithms.
result Provable prevention of privacy risks with strong learning bounds.
Differential privacy of Gaussian process posterior sampling
problem Privacy of posterior sample paths from Gaussian process
method Intrinsic randomness yields DP guarantees
result Intrinsic randomness yields DP guarantees