English

FedSecureFormer: A Fast, Federated and Secure Transformer Framework for Lightweight Intrusion Detection in Connected and Autonomous Vehicles

Cryptography and Security 2026-01-01 v1 Artificial Intelligence

Abstract

This works presents an encoder-only transformer built with minimum layers for intrusion detection in the domain of Connected and Autonomous Vehicles using Federated Learning.

Keywords

Cite

@article{arxiv.2512.24345,
  title  = {FedSecureFormer: A Fast, Federated and Secure Transformer Framework for Lightweight Intrusion Detection in Connected and Autonomous Vehicles},
  author = {Devika S and Vishnu Hari and Pratik Narang and Tejasvi Alladi and F. Richard Yu},
  journal= {arXiv preprint arXiv:2512.24345},
  year   = {2026}
}