preprint · techrxiv · 2025

Federated Learning-Based Intrusion Detection System for IoT Networks in Resource-Constrained Environments

abstract

A lightweight federated-learning intrusion detection system for resource-constrained IoT deployments. Training stays decentralized, which removes the privacy and communication costs of central data collection, and differential privacy keeps model updates from leaking through gradients. On NSL-KDD and IoT-23, the federated model reaches nearly the same detection performance as a centralized baseline while remaining deployable on constrained nodes.

@misc{nguyen2025federated,
  author = {Nguyen, Michel},
  title = {Federated Learning-Based Intrusion Detection System for IoT Networks in Resource-Constrained Environments},
  year = {2025},
  howpublished = {TechRxiv},
  doi = {10.36227/techrxiv.176403418.87468767/v1},
  url = {https://doi.org/10.36227/techrxiv.176403418.87468767/v1}
}