On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Distributed Privacy”

Tangent differential privacycs.LG

New privacy framework tailored to specific data distributions.

problem Protecting individual data points in decision-making processes.

method Introducing tangent differential privacy, a new form of differential privacy.

result Entropic regularization guarantees tangent differential privacy under general conditions.

differential privacy data protection risk minimization

2024-06-06abs ↗pdf ↗

Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraintsmath.ST

Paper studies optimal federated learning for nonparametric regression with privacy constraints.

problem Federated learning for nonparametric regression with heterogeneous differential privacy constraints.

method Proposes distributed privacy-preserving estimators and investigates their risk properties.

result Establishes matching minimax lower bounds for global and pointwise estimation.

federated learning nonparametric regression differential privacy Besov spaces privacy preservation

2024-06-10abs ↗pdf ↗

Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimizationcs.LG

Study optimizes privacy in distributed optimization, balancing accuracy and communication.

problem Privacy-preserving distributed stochastic convex optimization.

method Distributed algorithm using Vaidya's plane cutting method, with privacy guarantees via differential privacy.

result Complete characterization of accuracy-communication-privacy trade-off.

Privacy-preserving Distributed optimization Convex optimization Differential privacy Stochastic optimization

2025-01-06abs ↗pdf ↗

Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustnesscs.LG

New findings show privacy affects generalization error in a non-monotonic way.

problem Privacy and robustness in distributed learning.

method Theoretical analysis and matching lower/upper bounds on algorithmic stability.

result Generalization error is non-monotonically affected by privacy, depending on noise level.

Privacy Generalization Byzantine Robustness Distributed Learning Algorithmic Stability

2026-07-01abs ↗pdf ↗

Learning discrete distributions: user vs item-level privacycs.LG

New privacy mechanism for user-level discrete distributions with reduced penalty.

problem Achieving privacy for all items of a single user in practical applications.

method Study of learning discrete distributions with user-level differential privacy, proposing a new mechanism with reduced privacy penalty.

result Proposed mechanism reduces privacy penalty to

ilde{\mathcal{O}}(k/(mα^2) + k/\sqrt{m}εα)

, significantly smaller than standard mechanisms.

differential privacy user-level privacy discrete distributions federated learning privacy penalty

2020-07-27abs ↗pdf ↗

Universal Exact Compression of Differentially Private Mechanismscs.CR

Novel compression method preserves privacy while reducing communication costs.

problem Reducing communication costs in differential privacy mechanisms.

method Poisson private representation (PPR) for compressing and simulating local randomizers.

result Achieves compression within a logarithmic gap from theoretical lower bound.

differential privacy compression local randomizer simulation communication cost

2024-05-28abs ↗pdf ↗

Bayesian Differential Privacy for Machine Learningcs.LG

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…

2019-01-28abs ↗pdf ↗

Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanismsmath.ST

New methods test discrete distributions faster with local privacy constraints.

problem Testing discrete distributions under local differential privacy constraints.

method Efficient randomized algorithms and test procedures, both non-interactive and interactive.

result Faster separation rates in interactive privacy mechanisms.

local differential privacy distribution testing non-asymptotic multinomial polynomial

2020-05-26abs ↗pdf ↗

Compressive Sensing Approaches for Sparse Distribution Estimation Under Local Privacycs.IT

Paper optimizes privacy-preserving distribution estimation for sparse data.

problem Sparse distribution estimation under local differential privacy constraints.

method Compressive sensing approaches for privacy-preserving estimation.

result Significant reduction in sample complexity for approximately sparse distributions.

Privacy-preserving estimation Compressive sensing Local differential privacy Sparse distribution

2020-12-03abs ↗pdf ↗

Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketchescs.LG

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…

2019-11-03abs ↗pdf ↗

Differentially private cross-silo federated learningcs.CR

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.

differential privacy federated learning privacy amplification secure summation subsampled learning

2020-07-10abs ↗pdf ↗

The Skellam Mechanism for Differentially Private Federated Learningcs.LG

A new discrete privacy mechanism for federated learning.

problem Differentially private federated learning with communication constraints.

method Skellam mechanism based on Poisson distributions.

result Skellam mechanism provides similar privacy-accuracy trade-offs as Gaussian mechanism.

differential privacy federated learning secure aggregation Skellam mechanism Poisson distribution

2021-10-11abs ↗pdf ↗

Analyzing Inference Privacy Risks Through Gradients in Machine Learningcs.LG

Unified framework analyzes privacy risks from gradients in distributed learning.

problem Analyzing inference privacy risks from gradients in machine learning.

method Unified game-based framework for various attacks, including attribute, property, distributional, and user disclosures.

result Demonstrates inefficacy of data aggregation for privacy against inference attacks.

privacy inference attacks distributed learning gradients machine learning

2024-08-29abs ↗pdf ↗

Profile-Based Privacy for Locally Private Computationscs.CR

Differential privacy has emerged as a gold standard in privacy-preserving data analysis. A popular variant is local differential privacy, where the data holder is the trusted curator. A major barrier, however, towards a wider adoption of this model is that it offers a poor privacy-utility tradeoff. In this work, we add…

2019-01-21abs ↗pdf ↗

Preserving Differential Privacy Between Features in Distributed Estimationstat.ML

Privacy is crucial in many applications of machine learning. Legal, ethical and societal issues restrict the sharing of sensitive data making it difficult to learn from datasets that are partitioned between many parties. One important instance of such a distributed setting arises when information about each record in t…

2017-03-01abs ↗pdf ↗

Discrete Distribution Estimation under Local Privacystat.ML

The collection and analysis of user data drives improvements in the app and web ecosystems, but comes with risks to privacy. This paper examines discrete distribution estimation under local privacy, a setting wherein service providers can learn the distribution of a categorical statistic of interest without collecting …

2016-02-24abs ↗pdf ↗

Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learningcs.LG

New mechanism protects neural network weights from privacy attacks during self-supervised learning.

problem Privacy risks during fine-tuning stage of self-supervised learning.

method Proposes a novel differential privacy mechanism using additive logistic noise.

result Reduces membership inference attack accuracy to 50% while maintaining below 5% performance loss.

privacy-preserving self-supervised learning differential privacy logistic distribution membership inference

2022-05-25abs ↗pdf ↗

Uniformity Testing in the Shuffle Model: Simpler, Better, Fastercs.DS

Simpler, faster algorithm for uniformity testing in the shuffle model.

problem Testing uniformity of data in the shuffle model with privacy constraints.

method Simplified analysis and use of privacy amplification via shuffling.

result An algorithm with the same guarantees but simpler and more streamlined.

uniformity testing shuffle model privacy amplification differential privacy

2021-08-20abs ↗pdf ↗

Robust Estimation of Discrete Distributions under Local Differential Privacymath.ST

New method estimates discrete distributions while protecting privacy.

problem Estimating discrete distributions with local differential privacy.

method Combining robust learning and local differential privacy.

result Minimax estimation rate of

ε\sqrt{d/α^2 k}+\sqrt{d^2/α^2 kn}

under privacy constraint.

Privacy Estimation Differential Privacy Discrete Distributions Robust Learning

2022-02-14abs ↗pdf ↗

DP-ADMM: ADMM-based Distributed Learning with Differential Privacycs.LG

Alternating Direction Method of Multipliers (ADMM) is a widely used tool for machine learning in distributed settings, where a machine learning model is trained over distributed data sources through an interactive process of local computation and message passing. Such an iterative process could cause privacy concerns o…

2018-08-30abs ↗pdf ↗

Capacity Bounded Differential Privacycs.LG

Differential privacy, a notion of algorithmic stability, is a gold standard for measuring the additional risk an algorithm's output poses to the privacy of a single record in the dataset. Differential privacy is defined as the distance between the output distribution of an algorithm on neighboring datasets that differ …

2019-07-03abs ↗pdf ↗

The Poisson binomial mechanism for secure and private federated learningcs.CR

PBM mechanism improves privacy and accuracy in federated learning.

problem Secure and private federated learning with limited privacy budget.

method Poisson Binomial mechanism for discrete differential privacy.

result Achieves same privacy-accuracy trade-offs as Gaussian mechanism.

federated learning discrete differential privacy secure aggregation Rényi divergence private machine learning

2022-07-09abs ↗pdf ↗

Differentially Private Distributed Inferencecs.LG

Privacy-preserving inference for clinical trials using differential privacy.

problem Balancing knowledge sharing and privacy in healthcare data.

method Differential privacy (DP) applied to log-linear belief updates in distributed settings.

result Differentially private, distributed inference methods outperform existing techniques.

differential privacy distributed inference clinical trials log-linear models survival analysis

2024-02-13abs ↗pdf ↗

Privacy Amplification via Random Check-Inscs.LG

New method amplifies privacy in decentralized learning without centralized communication.

problem Privacy amplification in decentralized federated learning.

method Random check-in protocol for DP-SGD in FL.

result Privacy/accuracy trade-offs similar to subsampling/shuffling, but without server-initiated communication.

Privacy Amplification Federated Learning DP-SGD Random Check-in Decentralized Learning

2020-07-13abs ↗pdf ↗

Differential privacy for symmetric log-concave mechanismscs.CR

New privacy mechanism reduces error in query results.

problem Achieving privacy while minimizing noise in query results.

method Extended sufficient and necessary condition for

(ε, δ)

-differential privacy for symmetric and log-concave noise densities.

result Significantly lower mean squared errors than Laplace and Gaussian mechanisms.

differential privacy log-concave mechanisms minimize noise query results privacy-preserving scale

2022-02-23abs ↗pdf ↗

Breaking the Communication-Privacy-Accuracy Trilemmacs.LG

Paper addresses privacy and communication in distributed learning, achieving optimal performance.

problem Balancing privacy, communication, and accuracy in distributed learning and estimation.

method Developed novel encoding and decoding mechanisms for mean and frequency estimation under local differential privacy and communication constraints.

result Achieved optimal privacy and communication efficiency in mean and frequency estimation.

distributed learning privacy communication differential privacy frequency estimation

2020-07-22abs ↗pdf ↗

Optimal Differentially Private Sampling of Unbounded Gaussianscs.DS

Improved sampling from Gaussian distributions with privacy constraints.

problem Sampling from unbounded Gaussian distributions with differential privacy.

method First $\widetilde{\mathcal{O}}\left(d ight)$-sample algorithm for unbounded Gaussians under $\left(\varepsilon, δ ight)$-differential privacy.

result A quadratic improvement over previous results, settling an open question.

differential privacy sampling Gaussian distributions unbounded

2025-03-03abs ↗pdf ↗

Privacy-Preserving Community Detection for Locally Distributed Multiple Networkscs.SI

New method preserves privacy while detecting communities in distributed networks.

problem Privacy-preserving community detection in locally distributed multi-layer networks.

method Privacy-preserving Distributed Spectral Clustering (ppDSC) using randomized response mechanism.

result Developed a novel algorithm that maintains community structure while protecting privacy.

Privacy-preserving Community detection Distributed networks Randomized response Spectral clustering

2023-06-27abs ↗pdf ↗

Shared MF: A privacy-preserving recommendation systemcs.LG

SharedMF uses secret sharing to protect privacy in distributed recommendation systems.

problem Privacy issues in multi-source data for recommendation systems.

method Federated learning and secret sharing technology.

result SharedMF achieves faster execution speed and better data adaptability compared to homomorphic encryption methods.

matrix factorization recommendation system privacy-preserving Federated learning secret sharing

2020-08-18abs ↗pdf ↗

SAPAG: A Self-Adaptive Privacy Attack From Gradientscs.LG

SAPAG attacks distributed learning by reconstructing true training data from gradients.

problem Privacy attacks on distributed learning systems through gradients.

method SAPAG uses a Gaussian kernel-based gradient difference distance measure.

result SAPAG can reconstruct training data on various DNNs and at different training phases.

privacy attacks distributed learning federated learning collaborative learning gradient attacks

2020-09-14abs ↗pdf ↗

Differential Privacy at Risk: Bridging Randomness and Privacy Budgetcs.CR

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.

differential privacy privacy-preserving mechanisms randomness privacy guarantees composition theorem

2020-03-02abs ↗pdf ↗

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networksstat.ML

Our study analyzes how neural network initialization affects privacy and utility in overparameterized models.

problem Privacy and utility trade-off in overparameterized neural networks.

method Analytical proof of KL divergence privacy bound, focusing on initialization, width, and depth.

result Privacy bound improvement with increasing depth under certain initializations, degradation under others.

Privacy Utility Neural Networks Initialization KL Divergence

2023-10-31abs ↗pdf ↗

Individual Privacy Accounting with Gaussian Differential Privacycs.CR

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.

Gaussian differential privacy privacy accounting adaptive compositions Rényi differential privacy privacy loss distributions

2022-09-30abs ↗pdf ↗

Differentially Private Distributed Estimation and Learningcs.LG

Distributed estimation and learning with privacy preserved.

problem Privacy-preserving distributed estimation and learning in a networked environment.

method Linear aggregation schemes with differential privacy constraints.

result Noise minimizes convergence time to best estimates, using Laplace noise.

differential privacy distributed estimation learning networked environment private signals

2023-06-28abs ↗pdf ↗

Multi-Task Differential Privacy Under Distribution Skewcs.LG

New algorithm optimizes privacy and utility in multi-task learning with skewed data.

problem Privacy constraints in multi-task learning with uneven data distribution.

method Adaptive reweighting of privacy budget allocation among tasks.

result Significant improvement in utility with state-of-the-art performance on benchmarks.

differential privacy multi-task learning distribution skew user-level privacy empirical risk

2023-02-15abs ↗pdf ↗

Does Privacy Always Harm Fairness? Data-Dependent Trade-offs via Chernoff Information Neural Estimationcs.LG

Paper analyzes trade-offs between fairness, privacy, and accuracy using Chernoff Information.

problem The relationship between fairness and privacy in machine learning.

method Utilizes Chernoff Information to characterize trade-offs, proposes Chernoff Difference and Noisy Chernoff Difference, develops CINE for neural estimation.

result Shows three distinct behaviors of Noisy Chernoff Difference based on data distribution.

Chernoff Information Fairness Privacy Accuracy Machine Learning

2026-01-20abs ↗pdf ↗

Conformal-DP: A Density-Aware Mechanism for Differential Privacy over Riemannian Manifolds via Conformal Transformationcs.CR

Conformal-DP improves differential privacy on manifold data by calibrating perturbations based on local densities.

problem Lack of density-awareness in existing differential privacy mechanisms for manifold data leads to biased and suboptimal privacy-utility trade-offs.

method Proposes Conformal-DP, a density-aware differential privacy mechanism using conformal transformations to calibrate perturbations based on local densities.

result Demonstrates improved privacy-utility trade-off in heterogeneous data distribution settings compared to state-of-the-art mechanisms.

Differential Privacy Riemannian Manifolds Density-Aware Conformal Transformations Privacy Utility

2025-04-29abs ↗pdf ↗

Alleviating Privacy Attacks via Causal Learningcs.LG

Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such privacy risks are exacerbated when a model's predictions are used on an unseen data …

2019-09-27abs ↗pdf ↗

Fisher information under local differential privacycs.IT

Data processing inequalities link Fisher information to local differential privacy constraints.

problem Understanding how Fisher information scales with local differential privacy constraints.

method Developed data processing inequalities for Fisher information under local differential privacy.

result Implications for private estimation with optimal bounds and error rates.

Fisher information local differential privacy data processing inequalities private estimation order optimal bounds

2020-05-21abs ↗pdf ↗

The Discrete Gaussian for Differential Privacycs.DS

Discrete Gaussian noise preserves privacy and accuracy in differential privacy.

problem Finite computers cannot represent continuous Gaussian noise, leading to privacy breaches and loss of interpretability.

method Introduced and analyzed discrete Gaussian noise, providing privacy and accuracy guarantees similar to continuous Gaussian noise.

result Discrete Gaussian noise offers the same privacy and accuracy as continuous Gaussian noise, with efficient sampling algorithms.

differential privacy discrete Gaussian numerical errors integer queries counting queries

2020-03-31abs ↗pdf ↗

A Polynomial Time, Pure Differentially Private Estimator for Binary Product Distributionscs.DS

Efficiently estimates binary product distributions with privacy.

problem Estimating means of binary product distributions privately and accurately.

method Polynomial time, pure differential privacy approach.

result Optimal sample complexity with polylogarithmic factors.

differential privacy binary product distributions estimation polynomial time total variation distance

2023-04-13abs ↗pdf ↗

Edgeworth Accountant: An Analytical Approach to Differential Privacy Compositioncs.CR

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.

differential privacy privacy-preserving composition Edgeworth expansion privacy-loss log-likelihood ratios (PLLRs)

2022-06-09abs ↗pdf ↗

A Bias-Accuracy-Privacy Trilemma for Statistical Estimationmath.ST

Private statistics estimation faces a bias, accuracy, and privacy trilemma.

problem Balancing privacy, accuracy, and bias in statistical estimation.

method Use differential privacy (DP) for private statistics, but clip samples to control sensitivity and add noise for privacy, introducing bias.

result No algorithm can simultaneously have low bias, low error, and low privacy loss for arbitrary distributions.

differential privacy statistical estimation bias accuracy privacy

2023-01-30abs ↗pdf ↗

cpSGD: Communication-efficient and differentially-private distributed SGDstat.ML

Distributed stochastic gradient descent is an important subroutine in distributed learning. A setting of particular interest is when the clients are mobile devices, where two important concerns are communication efficiency and the privacy of the clients. Several recent works have focused on reducing the communication c…

2018-05-27abs ↗pdf ↗

Generating Synthetic Data with Locally Estimated Distributions for Disclosure Controlstat.CO

Paper introduces LR to generate synthetic data with privacy protection.

problem Privacy concerns limit the use of sensitive datasets.

method Local Resampler (LR) using k-nearest neighbors algorithm.

result LR effectively mitigates outlier-driven disclosure risks.

synthetic data disclosure control privacy protection k-nearest neighbors multimodal distributions

2022-10-03abs ↗pdf ↗

Differentially Private Assouad, Fano, and Le Camcs.LG

The paper extends statistical estimation techniques under differential privacy.

problem Establishing sample complexity bounds for estimation tasks under differential privacy.

method Proposes analogues of Le Cam's method, Fano's inequality, and Assouad's lemma under central differential privacy.

result Optimal sample complexity bounds for discrete distribution estimation under total variation and

\ell_2

distances.

differential privacy statistical estimation lower bounds coupling sample complexity

2020-04-14abs ↗pdf ↗

Learning with User-Level Local Differential Privacystat.ML

This paper analyzes user-level local differential privacy in distributed systems.

problem The relationship between user-level and item-level local differential privacy under the local model is complex.

method The paper analyzes the mean estimation problem and applies it to stochastic optimization, classification, and regression. It proposes adaptive strategies to achieve optimal performance at all privacy levels.

result The proposed methods are minimax optimal up to logarithmic factors and show that user-level DP can lead to faster convergence rates than item-level DP.

local differential privacy user-level privacy distributed systems stochastic optimization classification

2024-05-27abs ↗pdf ↗

Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraintsmath.ST

Paper tackles nonparametric classification with privacy constraints, achieving optimal accuracy.

problem Nonparametric classification under distributed differential privacy constraints.

method Minimax and adaptive transfer learning, considering privacy, sample sizes, and heterogeneity.

result Developed an adaptive classifier achieving optimal misclassification rate with privacy constraints.

minimax transfer learning nonparametric classification differential privacy heterogeneous data

2024-06-28abs ↗pdf ↗