From Flows to Words: Can Zero-/Few-Shot LLMs Detect Network Intrusions? A Grammar-Constrained, Calibrated Evaluation on UNSW-NB15

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rehman, Mohammad Abdul, Shah, Syed Imad Ali, Anwar, Abbas, Islam, Noor
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.17883