Minimalist LLMs for Network Attack Detection Via Quantization and Low-Rank Adaptation

Ur Rehman, Mohib; Rustam, Furqan; Obaidat, Islam; Jurcut, Anca Delia

Minimalist LLMs for Network Attack Detection Via Quantization and Low-Rank Adaptation

Tools

Ur Rehman, Mohib, Rustam, Furqan, Obaidat, Islam and Jurcut, Anca Delia (2025) Minimalist LLMs for Network Attack Detection Via Quantization and Low-Rank Adaptation. In: 2025 17th International Conference on Advanced Infocomm Technology (ICAIT). IEEE, Liaocheng, China, pp. 147-152. ISBN 979-833157912-8

Full text not available from this repository.

Official URL: https://doi.org/10.1109/ICAIT66450.2025.11353333

Abstract

Large Language Models (LLMs) are increasingly considered for network attack detection; however, their high computational footprint and generative design limit their suitability for real-time cybersecurity deployment. This work introduces a lightweight LLM-based framework for network attack detection that utilizes two LLMs, Gemma-2 and LLaMA-3.2, enhanced through quantization and calibration to make them efficient and accurate. The Low-Rank Adaptation (LoRA) framework is used to fine-tune the models for network traffic, improving their capability to understand traffic patterns. LoRA also reduces the number of trainable parameters by approximately 99%. The fine-tuned weights are further compressed to 4-bit float precision using the BitsAndBytes framework, and quantization quality is enhanced using the NormalFloat4 approach, yielding a 3−4× memory reduction without the need for retraining. Gemma-2 and LLaMA-3.2 achieve accuracies of 0.99 and 0.95, respectively, with LLaMA-3.2 providing a 0.022 s inference time per sample, suitable for real-time monitoring.

Item Type:	Book Section
Uncontrolled Keywords:	LLMs; Network Attack Detection; LoRA; Quantization; Transformers
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing
Depositing User:	Tamara Malone
Date Deposited:	14 Apr 2026 09:27
Last Modified:	14 Apr 2026 09:27
URI:	https://norma.ncirl.ie/id/eprint/9283

Actions (login required)

View Item