Llm improves automated intrusion detection in iot networks efficiently
An LLM-Assisted AutoML Framework for Intrusion Detection in IoT Networks
Cryptography and SecurityMachine Learning
Summary
IoT devices connect many everyday things to the internet but can be vulnerable to attacks. Machine learning can help spot these attacks, but setting up the learning system is complicated and usually requires expert decisions. The authors show how using a large language model (LLM) can guide the setup process, making it faster and more accurate than traditional automated methods. Their approach tested on two IoT datasets outperformed standard techniques while using less optimization time.
What this means in practice
- •For network security teams: Deploy automated intrusion detection tailored to IoT networks that improves detection accuracy and reduces tuning time using LLM-guided ML pipelines.
- •For cybersecurity product developers: Implement faster optimization of ML models for IoT security products by integrating LLM-generated policies to cut search time and improve model quality.$Commercial implications: Enables development of advanced IoT intrusion detection tools with reduced trial counts and better performance, appealing to security vendors.
Authors
Li Yang
Abstract
Internet of Things (IoT) systems are increasingly deployed in smart homes, transportation, energy systems, and critical infrastructure. This broad connectivity improves service intelligence, but also enlarges the attack surface of IoT networks. Machine Learning (ML)-based Intrusion Detection Systems (IDSs) are widely used to identify malicious network threats and protect IoT systems, but developing effective ML-based IDS models often requires human expertise and repeated manual decisions on many procedures, including data pre-processing, feature selection, model selection, and hyperparameter tuning. Automated Machine Learning (AutoML) reduces this burden by automating steps of the ML pipeline using optimization techniques, but conventional AutoML methods can consume substantial optimization time because they explore broad candidate model families and large hyperparameter spaces. This paper proposes a Large Language Model (LLM)-assisted AutoML framework for IoT intrusion detection. The proposed framework uses an LLM as a policy generator that converts dataset profiles into bounded and validated AutoML policies for automated data balancing, automated feature engineering, and Combined Algorithm Selection and Hyperparameter Optimization (CASH). Under an equal 10-trial budget, the proposed LLM-assisted policy achieves higher weighted test F1-score than traditional AutoML using the Tree-structured Parzen Estimator (TPE) on both datasets, reaching 99.680% on CICIDS2017 and 99.186% on IoTID20. Relative to the broader 30-trial Traditional AutoML-TPE baseline, the 10-trial proposed method reduces optimizer time by 63.7% and 49.9%, respectively, while achieving slightly higher F1-score. These results show that a bounded LLM policy can improve the quality of a low-budget AutoML search while retaining a clear efficiency advantage relative to a larger conventional search budget.