Overview of Adversarial AI and Data Poisoning in Federated Learning

Abstract

Federated Learning (FL) is an emerging decentralized machine learning paradigm that enables multiple clients to collaboratively train a global model without sharing raw data, thereby preserving data privacy. . In adversarial settings, malicious clients can inject carefully crafted inputs or manipulate local training updates to degrade the global model's performance or embed backdoors. Data poisoning attacks, including label flipping and model update manipulation, pose significant threats by subt

Categories

Framework mappings

Suggested from the entry's categories.

@article{sheikh2026overview,
  title = {{Overview of Adversarial AI and Data Poisoning in Federated Learning}},
  author = {Mohammed Firdos Alam Sheikh},
  year = {2026},
  month = feb,
  journal = {Advances in Computational Intelligence and Robotics},
  doi = {10.4018/979-8-3373-6224-3.ch002},
  url = {https://doi.org/10.4018/979-8-3373-6224-3.ch002}
}