Latest Articles for Data Privacy

Testing LLMs is essential for safe and effective AI applications.

Examining attitudes towards donating health data after passing away.

A new framework for analyzing data streams while ensuring user privacy.

A novel method enhances personalized learning for large language models.

Exploring privacy threats in image processing using diffusion models and leaked gradients.

Analyzing data privacy through Bayesian inference with constraints.

Machine unlearning offers a way to improve data privacy in machine learning models.

New method targets rhythm changes for stealthy speech attacks.

Exploring the significance of unlearning methods in modern machine learning.

New method improves dataset condensation for better machine learning outcomes.

Exploring the synergy between federated learning and swarm intelligence for improved AI.

HiFGL framework addresses challenges in privacy-focused collaborative learning.

A fresh approach to create synthetic data without privacy concerns.

A new method improves federated learning for multi-modal data despite missing information.

Learn how target unlearning safeguards privacy by allowing models to forget specific information.

A new method to verify machine unlearning effectively and securely.

This method effectively removes copyrighted material while maintaining model performance.

This article discusses feature unlearning and its impact on privacy and fairness in machine learning.

This article discusses soft prompting as a method for machine unlearning in LLMs.

P3GNN enhances APT detection while protecting data privacy in SDN networks.

Examining memorization in code completion models and its privacy implications.

New methods reveal challenges in unlearning knowledge from language models.

Recommender systems influence user experiences but face key concerns regarding fairness and privacy.

A method to maintain privacy while sharing urban traffic statistics.

A framework to improve APT detection while protecting privacy.

LDMeta enhances privacy and efficiency in distributed learning methods.

The study examines how influencer ads shape VPN perceptions and online safety beliefs.

Exploring the synergy between Foundation Models and Federated Learning for enhanced AI applications.

A new method improves federated learning by using only one image for training.

Two robots improve maze navigation through shared learning experiences while maintaining data privacy.

New method combines federated learning with diffusion models for privacy-focused image generation.

A method to enhance data privacy in federated learning by removing specific data influences.

Snap helps large language models unlearn specific information while keeping their performance.

WavRx analyzes speech for health while protecting privacy, showing promising diagnostic results.

A new model enhances synthetic EHR data for improved healthcare applications.

This article explores how differential privacy safeguards ECG data in healthcare.

Fed-Grow allows users to build larger models together while protecting privacy.

This article explores strategies for protecting individual privacy in machine learning.

Fed-RAA enhances federated learning by adapting to client resources for faster training.

A new approach in federated learning captures data dependencies while ensuring privacy.