US EditionPublished • loading... • Updated
Securing DFL: Gradient Purification Defense Against Poisoning
Summary by Newswise
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.1 Articles
1 Articles
Securing DFL: Gradient Purification Defense Against Poisoning
Addressing vulnerabilities in Decentralized Federated Learning (DFL) against data poisoning, researchers from Zhejiang University proposed the Gradient Purification Defense (GPD). By utilizing a recording variable to track historical gradients, GPD identifies malicious neighbors and purifies model weights without full re-training.
·Charlottesville, United States
Read Full ArticleCoverage Details
Total News Sources1
Leaning Left0Leaning Right0Center0Last UpdatedBias DistributionNo sources with tracked biases.
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
