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