Research
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.

168,695 papers · 148 categories

Trend · papers per month

127253380506 · Jun 202019922001200920172026
48 results for privacy analysis

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.

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.

Addresses theoretical and practical aspects of Gaussian differential privacy.

problem Theoretical and practical challenges in privacy-preserving data analysis.
method Discussion of f-differential privacy and Gaussian differential privacy.
result Gaussian differential privacy can enhance privacy in various applications.

DP-SGD analysis shows many datapoints leak less privacy than previously thought.

problem Empirical evidence suggests DP-SGD leaks less privacy than current analysis predicts.
method Developed a per-instance DP analysis of DP-SGD, introducing dependence on dataset distribution.
result Formally shows DP-SGD leaks significantly less privacy for many datapoints on common benchmarks.

Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural networks subject to privacy constraints that are specified by differential…

2019-11-26abs ↗pdf ↗

The paper proposes methods to infer from privacy-protected data using simulation-based techniques.

problem Valid statistical inference from privacy-protected data is computationally challenging.
method Simulation-based inference methods, including sequential Monte Carlo and neural conditional density estimators.
result Valid statistical inferences can be made from privacy-protected data.

The paper analyzes privacy leakage in federated learning using linear algebra and optimization theory.

problem Privacy leakage in federated learning despite its promise for data privacy.
method Theoretical analysis from linear algebra and optimization theory perspectives.
result Derives sufficient conditions to prevent data reconstruction attacks and establishes an upper bound on privacy leakage.

New method shows hidden state can significantly improve differential privacy in SGD.

problem Differential privacy in SGD with hidden state.
method Proves converging privacy bounds for hidden state SGD, using privacy amplification techniques.
result Privacy bound converges exponentially fast and is smaller than composition bounds.

Paper develops novel privacy mechanism for Riemannian manifold data using geometric analysis and heat diffusion.

problem Privacy-preserving estimation of generalized Frechet mean on Riemannian manifolds.
method Characterizes Renyi divergence via Harnack inequalities, introduces mechanisms based on heat diffusion and Langevin process.
result Proposes mechanisms for nonnegative and general Riemannian manifolds with detailed utility analyses.

Paper evaluates and mitigates privacy risks in deep learning models.

problem Quantifying and defending against privacy attacks in deep learning.
method Quantitative evaluation of trade-offs, reformulating attacks, and proposing a novel SPN.
result Model accuracy improved by 5-20% while maintaining data privacy.

Differential privacy is a statistical concept that can be explained through hypothesis testing.

problem Formalizing differential privacy as a statistical concept.
method Using David Blackwell's informativeness theorem, the paper shows differential privacy can be understood through hypothesis testing.
result The definition of ff-differential privacy provides a unified framework for analyzing privacy bounds.

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.

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.

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 improves privacy and utility of SGD with bounded domain and smooth losses.

problem Lack of tight privacy bounds and practical assumptions in DPSGD.
method Rigorous privacy characterization for DPSGD with general L-smooth and non-convex loss functions, tracking privacy loss over iterations.
result Privacy loss converges without convexity assumption for bounded domain, improving utility.

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.

Classifies privacy policy segments for better user understanding.

problem Difficulty in understanding privacy policies due to legal jargon.
method Uses machine learning and deep learning techniques to classify privacy policy segments.
result Identifies data practices in privacy policies for better user comprehension.

Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To address this, we propose element level differential privacy, which extends differ…

2019-12-05abs ↗pdf ↗

Improved privacy analysis for stochastic gradient descent.

problem Analyzing privacy leakage in noisy stochastic gradient descent.
method Modeling Rényi divergence dynamics with Langevin diffusions, proving exponential privacy loss convergence for smooth and strongly convex objectives.
result Privacy loss converges exponentially fast for smooth and strongly convex objectives under constant step size.

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)(\varepsilon,δ)-values, demonstrating up to 75% reduction in noise variance.

This paper enhances privacy-preserving randomized power method for large datasets.

problem Privacy issues in applying randomized power method to large datasets containing personal information.
method Proposes enhanced privacy-preserving variants of the randomized power method, including a variant with reduced noise and a decentralized framework.
result Tighter convergence bounds and empirical comparisons with previous work in real recommendation datasets.

New analysis shows SGD with noise doesn't leak more privacy with more iterations.

problem Privacy loss in noisy SGD with more iterations.
method Privacy Amplification by Iteration and Sampled Gaussian Mechanism.
result Privacy loss remains constant after a burn-in period, not increasing with more iterations.

The paper analyzes and proposes methods for privately sharing individual privacy losses using per-instance differential privacy.

problem The standard differential privacy framework provides a worst-case bound that may not accurately reflect individual privacy losses.
method The paper analyzes per-instance differential privacy and proposes methods to privately and accurately publish per-instance privacy losses.
result The methods privately and accurately publish per-instance differential privacy losses with minimal additional privacy cost.

Many commonly used learning algorithms work by iteratively updating an intermediate solution using one or a few data points in each iteration. Analysis of differential privacy for such algorithms often involves ensuring privacy of each step and then reasoning about the cumulative privacy cost of the algorithm. This is …

2018-08-20abs ↗pdf ↗

This paper analyzes privacy-preserving methods for collaborative forecasting.

problem Data owners' reluctance to share data due to competitive and privacy concerns.
method Examines three groups of privacy-preserving methods: data transformation, secure multi-party computations, and decomposition methods.
result State-of-the-art techniques have limitations in preserving data privacy, such as trade-offs between privacy and forecasting accuracy.

Novel privatization framework for high-dimensional variable selection with differential privacy.

problem High-dimensional controlled variable selection with rigorous FDR control under differential privacy constraints.
method Gaussian Johnson-Lindenstrauss Transformation for privatizing the knockoff matrix.
result The proposed private variable selection procedure maintains statistical power even under strict privacy budgets.

PGFL framework learns personalized models with differential privacy.

problem Privacy-preserving personalized learning for diverse data.
method Exploits model similarities and differential privacy (zero-concentrated).
result Algorithm converges to optimal solutions with linear time complexity.

Differentially private log-location-scale regression models improve privacy in statistical analysis.

problem Ensuring privacy in statistical regression models while maintaining accuracy.
method Integrates differential privacy into LLS regression using the functional mechanism.
result Proposed DP-LLS models satisfy ε-differential privacy and perform well under various conditions.

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.

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)(\varepsilon,δ)-differential privacy bounds.
result Accurately evaluates privacy loss distribution for adaptive compositions of shufflers.

This paper bounds min-entropy leakage for Blowfish privacy using graph symmetries.

problem Bounding min-entropy leakage for Blowfish privacy mechanisms.
method Organizing analysis over symmetrical partitions corresponding to orbits of graph automorphism groups.
result Demonstrates a construction meeting the bound with asymptotic equality, showing tightness.

Paper presents a fast, private MH algorithm for large-scale Bayesian inference.

problem Privacy-preserving Bayesian inference for large-scale data.
method Developed a novel DP-MH algorithm using minibatches.
result First exact and fast DP MH algorithm with privacy, scalability, and efficiency trade-offs.

This paper sharpens privacy guarantees for high-dimensional PCA under differential privacy.

problem Understanding the exact privacy loss in high-dimensional PCA with differential privacy.
method Analyzes the exponential mechanism in a model-free setting for high-dimensional PCA.
result Sharp utility and privacy characterizations in high dimensions show the difficulty of detecting a target individual's presence.

This work analyzes DP-SGD for online LDP problems with practical convergence rates.

problem Analyzing DP-SGD for online LDP problems with practical convergence rates.
method Developed a general framework for online LDP model in stochastic optimization problems, conducted non-asymptotic convergence analysis.
result Comprehensive non-asymptotic convergence analysis of the proposed estimators in finite-sample situations.

Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses, either in handling composition of private algorithms or in analyzing important primi…

2019-05-07abs ↗pdf ↗