English

WiFi Pathologies Detection using LLMs

Signal Processing 2025-06-10 v1 Networking and Internet Architecture

Abstract

In this paper, we fine-tune encoder-only and decoder-only large language models (LLMs) to detect pathologies in IEEE 802.11 networks, commonly known as WiFi. Our approach involves manually crafting prompts followed by fine-tuning. Evaluations show that the sequential model achieves high detection accuracy using labeled data, while the causal model performs equally well for unlabeled data.

Cite

@article{arxiv.2506.06943,
  title  = {WiFi Pathologies Detection using LLMs},
  author = {Forough Shirin Abkenar},
  journal= {arXiv preprint arXiv:2506.06943},
  year   = {2025}
}
R2 v1 2026-07-01T03:05:14.500Z