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

84168251335 · Jun 202019922001200920172026
48 results for privacy measurement

A privacy-constrained information extraction problem is considered where for a pair of correlated discrete random variables (X,Y)(X,Y) governed by a given joint distribution, an agent observes YY and wants to convey to a potentially public user as much information about YY as possible without compromising the amount of …

2015-11-07abs ↗pdf ↗

The paper explores how to measure and optimize ad reach while maintaining user privacy.

problem Measuring ad reach while preserving user privacy in online advertising.
method Introduces kk-anonymity and probabilistic discounting for frequency capping.
result Privacy introduces a significant performance drop but with manageable costs.

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.

This paper introduces a novel approach to measuring privacy risks in deep computer vision models based on intermediate outputs.

problem The exposure of intermediate results in hidden layers of deep computer vision models poses significant privacy concerns.
method The approach leverages Degrees of Freedom (DoF) to evaluate the amount of information retained in each layer and combines this with the rank of the Jacobian matrix to assess sensitivity to input variations.
result The proposed framework provides deeper insights into privacy risks associated with intermediate representations without requiring adversarial attack simulations.

Paper improves privacy-preserving measurement of advertising incrementality.

problem Privacy degradation in randomized lift tests for advertising measurement.
method Formulates a robust causal decision problem under signal losses, projecting clean worlds onto incrementality.
result Sharp decision frontier shows valid certification or rejection outside the frontier.

Many modern databases include personal and sensitive correlated data, such as private information on users connected together in a social network, and measurements of physical activity of single subjects across time. However, differential privacy, the current gold standard in data privacy, does not adequately address p…

2016-03-13abs ↗pdf ↗

Differential privacy is a mathematical framework for privacy-preserving data analysis. Changing the hyperparameters of a differentially private algorithm allows one to trade off privacy and utility in a principled way. Quantifying this trade-off in advance is essential to decision-makers tasked with deciding how much p…

2019-05-26abs ↗pdf ↗

New MCMC method estimates differential privacy from multiple MIAs without worst-case assumptions.

problem Bayesian estimation of differential privacy from membership inference attacks.
method Bayesian estimation via MCMC algorithm (MCMC-DP-Est).
result More cautious privacy analysis with joint estimation of MIA strengths and privacy parameter.

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.

Paper develops a new method for differential privacy sampling using Wasserstein distance.

problem Sampling from distributions under differential privacy constraints with geometric structure consideration.
method Develops a novel framework with Wasserstein Projection Mechanism (WPM) for minimax optimal mechanisms.
result Proposes efficient algorithms for approximate computation of the Wasserstein Projection Mechanism.

We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of statistical estimation procedures. As a consequence, we exhibit a precise tradeoff be…

2012-10-07abs ↗pdf ↗

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.

Smart Meters (SMs) are able to share the power consumption of users with utility providers almost in real-time. These fine-grained signals carry sensitive information about users, which has raised serious concerns from the privacy viewpoint. In this paper, we focus on real-time privacy threats, i.e., potential attacker…

2019-06-14abs ↗pdf ↗

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.

Differentially private GANs improve image privacy without significant quality loss.

problem Anonymizing image data sets while maintaining image quality.
method Training GANs with differential privacy on MNIST, analyzing privacy-utility trade-offs and explaining optimization methods.
result An increasing privacy budget adds little to generated image quality, revealing a saturated training regime.

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 ↗

Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, εε, about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of εε in order to get acceptable utility of …

2019-02-24abs ↗pdf ↗

This paper quantifies privacy-robustness and generalization-robustness trade-offs in adversarial training.

problem Privacy and generalization issues in adversarial training.
method Defines robustified intensity and empirical robustified intensity to measure robustness, proving differential privacy and generalization bounds.
result Proves adversarial training is (ε,δ)(\varepsilon, δ)-differentially private and provides generalization bounds.

The US Census Bureau corrupts data to protect privacy, but we show how to clean and analyze it effectively.

problem Analyzing Census data with intentional corruption to maintain privacy.
method Formulated a semiparametric model, proposed data cleaning, estimation, and inference procedures.
result Demonstrated that data cleaning can maintain precision and provided theoretical and empirical support.

Sherpa.ai framework combines federated learning and differential privacy for edge AI services.

problem Protecting data privacy in edge AI services.
method Holistic federated learning and differential privacy approach with methodological guidelines.
result Demonstrated through classification and regression use cases.

Differential privacy is a framework for privately releasing summaries of a database. Previous work has focused mainly on methods for which the output is a finite dimensional vector, or an element of some discrete set. We develop methods for releasing functions while preserving differential privacy. Specifically, we sho…

2012-03-12abs ↗pdf ↗

Researchers found PP-GANs can hide sensitive data in sanitized images, undermining privacy checks.

problem Lack of formal proofs of privacy in PP-GANs for image sanitization.
method Subverted PP-GANs for facial expression recognition to hide sensitive data in sanitized images.
result It is possible to hide sensitive identification data in sanitized PP-GAN output images, even allowing reconstruction of entire input images.

Privacy affects fairness in classification models, but not drastically.

problem The impact of differential privacy on fairness in classification models.
method Theoretical analysis proving Lipschitz continuity of fairness measures and a non-asymptotic bound on fairness levels.
result Privacy impacts fairness, but not significantly as the number of samples increases.

Framework evaluates quality of synthetic data generated with differential privacy.

problem Ensuring synthetic data retains statistical quality after applying differential privacy.
method Developed a framework to evaluate synthetic data quality from a practical researcher's viewpoint.
result Synthetic data can be evaluated against training data or underlying populations, and for specific tasks like inference or prediction.

This work studies formal utility and privacy guarantees for a simple multiplicative database transformation, where the data are compressed by a random linear or affine transformation, reducing the number of data records substantially, while preserving the number of original input variables. We provide an analysis frame…

2009-01-10abs ↗pdf ↗

This paper improves privacy and fairness in federated learning by protecting sensitive data and ensuring group fairness.

problem Privacy and fairness issues in federated learning.
method Introduces group privacy through dd-privacy, a localized form of differential privacy.
result The method provides better group fairness than a global model in federated learning.

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.

The paper addresses learner privacy in convex optimization with feedback.

problem Privacy risks from eavesdropping adversaries observing learner's queries.
method Optimally obfuscating learner's queries to make their learned optimal value hard to estimate.
result Query complexity overhead is additive in LL in the minimax formulation, multiplicative in LL in the Bayesian formulation.

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.

In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA is a generalization of randomization techniques which includes random projections, lossy quantization, and addition of ambiguization noise t…

2019-05-08abs ↗pdf ↗

This paper addresses privacy issues in personalized pricing using nonparametric demand models.

problem Privacy violation in personalized pricing algorithms with unknown nonparametric demand models.
method Develops algorithms to make pricing decisions and learn demand while ensuring central and local differential privacy.
result Proves near-optimal regret bounds for algorithms with CDP and LDP guarantees.

DP-CDA generates synthetic data to enhance privacy in high-dimensional datasets.

problem Privacy concerns in anonymized datasets, especially in high-dimensional data.
method Randomized mixing of privacy-sensitive data in a class-specific manner with carefully tuned randomness.
result DP-CDA provides stronger privacy guarantees compared to existing methods, maintaining utility.