Blockchain-Based Swarm Learning for the Mitigation of Gradient Leakage in Federated Learning
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3246126
Abstract: Federated Learning (FL) is a machine learning technique in which collaborative and distributed learning is performed, while the private data reside locally on the client. Rather than the data, only gradients are shared among all… read more here.
Keywords: federated learning; blockchain based; gradient leakage; based swarm ... See more keywords
Gradient Leakage Attacks in Federated Learning: Research Frontiers, Taxonomy, and Future Directions
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Network"
DOI: 10.1109/mnet.001.2300140
Abstract: Federated learning (FL) is a distributed deep learning framework that has become increasingly popular in recent years. Essentially, FL supports numerous participants and the parameter server to co-train a deep learning model through shared gradients… read more here.
Keywords: analytics based; leakage attacks; future directions; gradient leakage ... See more keywords
The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks Through Model Poisoning
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2025.3607271
Abstract: In Federated Learning (FL), clients share gradients with a central server while keeping their data local. However, malicious servers could deliberately manipulate the models to reconstruct clients’ data from shared gradients, posing significant privacy risks.… read more here.
Keywords: gradient puppeteer; leakage; existing aglas; leakage attacks ... See more keywords
Securing Distributed SGD Against Gradient Leakage Threats
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Parallel and Distributed Systems"
DOI: 10.1109/tpds.2023.3273490
Abstract: This paper presents a holistic approach to gradient leakage resilient distributed Stochastic Gradient Descent (SGD). First, we analyze two types of strategies for privacy-enhanced federated learning: (i) gradient pruning with random selection or low-rank filtering… read more here.
Keywords: securing distributed; privacy; gradient leakage; gradient ... See more keywords