Latest Articles for Data Privacy

FedHPL enhances federated learning efficiency while ensuring data privacy across devices.

A new method enables the transfer of LoRA modules with synthetic data, minimizing reliance on original data.

This study improves the security of quantum machine learning against adversarial attacks through noise channels and privacy methods.

Fast-FedUL provides quick data removal methods for federated learning while ensuring privacy.

New methods enhance data removal processes in machine learning models.

KALM4Rec enhances recommendations for new users using keyword-driven methods.

Learn how data minimization protects privacy amidst growing data collection.

New methods reduce memorization risks in medical imaging with diffusion models.

FeMLoc improves indoor localization using federated and meta-learning techniques.

This article discusses differential privacy's impact on trust in the U.S. Census.

A new method to enhance exemplar-free continual learning by tracking class representation changes.

FedGELA tackles challenges in federated learning with partially class-disjoint data.

A new method for federated learning that addresses continual learning challenges.

FedLESAM tackles data challenges in federated learning for better model performance.

Exploring methods to secure patient information in clinical research.

FedMR tackles challenges in federated learning with partial class data, enhancing model performance.

PadFL improves model sharing and efficiency across varying device capabilities.

Federated Learning trains models while keeping user data private and secure.

AI tools support negotiators in complex environments, enhancing efficiency and decision-making.

A method to rewrite texts while protecting individuals' privacy.

A new approach enhances security and performance in federated learning with blockchain.

Study reveals how mobile apps shape travel behavior insights.

Examining client contributions and vulnerabilities in federated learning systems.

A method for collaborative machine learning while keeping data private.

New methods for privacy-preserving collaboration in vertical federated learning.

Exploring federated control in reinforcement learning for agents to work together securely.

Forgetting enhances learning in humans and machine models, improving adaptability and performance.

A new method improves data privacy for discrete data analysis.

SpaFL enhances communication and computation in Federated Learning while securing personal data.

LayerCAM-AE enhances detection of malicious updates in federated learning while preserving data privacy.

Research aims to balance privacy and accuracy in vector mean estimation methods.

Counterfactuals reveal insights but pose privacy risks in machine learning.

Examining the risks and misuse of large language models in cybercrime.

A new method tackles wireless errors in federated learning for IoT devices.

This article discusses privacy and bias in predictive algorithms for sensitive data.

A new method enhances model predictions for better adaptation without source data.

A new framework enhances synthetic data creation while protecting personal information.

A new multi-server approach improves federated learning efficiency and speed.

Introducing PrivacyRestore to protect user data while using large language models.

This study addresses difficulties in unlearning data from machine learning models.