Latest Articles for Data Privacy

Integrating explainable AI into 6G enhances user trust and performance.

Examining the balance between data sharing and patient privacy in biomedical research.

Exploring privacy risks and strategies for managing data leakage in language models.

FedBug tackles client drift while enhancing federated learning efficiency and privacy.

Epsilon* evaluates privacy risks in machine learning without needing sensitive data access.

A comprehensive dataset sheds light on Wi-Fi probe requests and user privacy.

Research shows promise in using synthetic images for effective polyp segmentation.

A new method for improved fairness in federated learning client selection.

This article introduces new techniques to enhance differential privacy in model training.

A look at communication security in decentralized federated learning systems.

New methods improve model training efficiency and privacy in deep learning.

Examining how to protect personal health data in metaverse healthcare systems.

A new method to improve supply chain analytics while respecting data privacy.

Innovative approaches enhance data privacy and model performance in connected devices.

Exploring the security challenges and solutions in the evolving Web 3.0 landscape.

This article discusses importance sampling and its role in maintaining data privacy.

Exploring AI's role in managing complex 6G network demands.

HeteFedRec improves federated recommendation systems while protecting user privacy.

FedDRL enhances federated learning by focusing on model quality and security.

This study examines methods to protect privacy while analyzing spoken conversations.

Examining the vulnerabilities of random rounding in Canadian census data.

This study analyzes how packet loss affects performance in Split-Federated Learning.

Explore the Node Injection Link Stealing attack and privacy concerns in GNNs.

Exploring advanced methods to enhance data privacy in machine learning using quantum techniques.

A look at splitfed learning and its benefits for IoT devices.

Jellybean, a novel technique, enables secure connections without shared secrets.

SIP balances data sharing and privacy for real-time applications.

Anonymized movement data sheds light on human behavior in cities.

A tool for maintaining confidentiality and integrity in research data management.

Federated Learning enables secure model training without exposing personal data.

A look into the rise of larger IPv6 address lists and their implications.

Education 5.0 blends technology with personalized learning for all students.

Federated Learning enhances statistical accuracy while protecting individual privacy in data collection.

Exploring privacy issues in fine-tuning AI models like GPT-3.

A new approach to improve private data trading accuracy and privacy.

A fresh approach to protect privacy in time series data analysis.

AQUILA enhances federated learning by optimizing device selection and data communication.

A new method improves federated learning while preserving patient data privacy.

A new model safeguards user movements while ensuring data utility.

FPGAs improve the efficiency and safety of Federated Learning processes.