Latest Articles for Differential Privacy

New methods generate synthetic data to protect privacy in collaborative scenarios.

A new approach to boxplots ensures data privacy while maintaining insightful analysis.

This article discusses creating reliable hypothesis tests despite data corruption.

Examining the relationship between privacy techniques and biases in language models.

New methods improve privacy and coherence using collocations in language data.

A new method for rewriting text that ensures privacy and maintains meaning.

This study assesses advanced models for generating fake trip data and their practical applications.

A method for estimating community memberships while protecting individual privacy.

Cities gain crucial transport data while addressing privacy concerns.

Examining differential privacy's effectiveness in protecting individual identities in SOEP data.

Creating systems that promote truthfulness among users in various digital interactions.

This research discusses federated learning's role in protecting privacy during data analysis.

New methods for statistical testing while protecting data privacy through federated learning.

Exploring challenges and advancements in protecting sensitive data while maintaining its usefulness.

Data-driven techniques must protect privacy while identifying the best options.

The challenge of combining differential privacy with sublinear algorithms in data analysis.

A look at federated learning combining differential privacy and blockchain for data security.

A new model improves data privacy while enhancing machine learning accuracy.

A fresh method to compare privacy mechanisms in machine learning.

A new method improves privacy while training deep learning models.

This article discusses methods to keep agents' decision-making processes private.

Federated learning enhances medical imaging while protecting patient data.

Examining differential privacy and NTK regression to protect user data in AI.

A closer look at disclosure risks in synthetic data and privacy protection.

Exploring differential privacy to protect sensitive information in AI applications.

Examining the role of robustness in estimating unknown distributions from samples.

PUFFLE offers a solution for privacy, utility, and fairness challenges in machine learning.

This method enhances privacy while improving model accuracy in AI.

A study on balancing transfer learning and individual privacy in data usage.

This paper discusses the Poisson mechanism for maintaining privacy in data synthesis.

Examining privacy risks in model explanations and strategies to enhance security.

Exploring Quantum Local Differential Privacy to safeguard quantum data.

New methods enhance privacy and communication in federated learning.

Examining differential privacy in natural language processing for better data protection.

Defogger offers new strategies for exploring sensitive data while ensuring privacy.

This article discusses federated learning methods and their impact on privacy and model utility.

A new method addresses privacy challenges in estimating U-statistics accurately.

A new method for privacy-preserving density estimation using stable list decoding.

Examining privacy concerns with task-oriented communication in the upcoming 6G technology.

A new method enhances privacy for facial images while retaining quality.