A Meta-Reinforcement Learning-Based Poisoning Attack Framework Against Federated Learning

A Meta-Reinforcement Learning-Based Poisoning Attack Framework Against Federated Learning

As a distributed machine learning paradigm, federated learning enables clients to collaboratively train a global model without sharing their raw data, thus preserving data privacy while still utilizing the data. However, the distributed nature of federated learning makes it vulnerable to poisoning a...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Zhou, Donglai Zhang, Hongjie Wang, Jinliang Li, Mingjian Jiang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Federated learning
poisoning attack
meta-reinforcement learning
generative adversarial network
robust aggregation strategy
Online Access:https://ieeexplore.ieee.org/document/10872904/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10872904/

Similar Items