发表机构
Ontario Tech University; Western University（安大略理工大学; 西安大略大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对电动汽车充电网络的安全需求，该研究提出基于多目标自动机器学习的入侵检测系统，采用轻量级训练与多目标优化，在两个数据集上实现了检测性能、延迟与模型规模的平衡。
AI 中文摘要
电动汽车充电系统（EVCS）正日益与物联网（IoT）设备连接，这提升了充电智能化程度，但也扩大了其受网络攻击的暴露面。入侵检测系统（IDS）对保障电动汽车充电网络安全至关重要；然而，传统基于机器学习（ML）的IDS往往依赖人工模型设计，且主要优化检测性能，未充分考虑推理延迟与模型规模。本文提出一种基于多目标自动机器学习（MOO-AutoML）的高效IDS，用于EVCS安全。该框架采用轻量级训练策略与基于LightGBM的自动特征选择方法，依据累积特征重要性选择紧凑特征子集；随后，非支配排序遗传算法III（NSGA-III）在三个目标下联合优化特征选择阈值与关键LightGBM超参数：最大化加权F1分数、最小化第99百分位推理延迟比、最小化模型规模比。在CICEVSE2024与CICIDS2017数据集上的实验表明，所提MOO-AutoML IDS相较于对比方法，取得了具有竞争力的加权F1分数、更低的P99推理延迟以及更小的模型规模。总体而言，结果表明所提方法可在实际部署约束下为EVCS及物联网安全提供准确高效的入侵检测支持。
英文摘要
Electric Vehicle Charging Systems (EVCSs) are increasingly connected with Internet of Things (IoT) devices, which improves charging intelligence but also expands their exposure to cyber-attacks. Intrusion Detection Systems (IDSs) are essential for securing EV charging networks; however, conventional Machine Learning (ML)-based IDSs often rely on manual model design and mainly optimize detection performance without fully considering inference latency and model size. In this paper, a Multi-Objective Automated ML (MOO-AutoML)-based efficient IDS is proposed for EVCS security. The proposed framework uses a lightweight training strategy and a LightGBM-based automated feature selection method to select compact feature subsets based on accumulated feature importance. Then, Non-dominated Sorting Genetic Algorithm III (NSGA-III) jointly optimizes the feature selection threshold and key LightGBM hyperparameters under three objectives: maximizing weighted F1-score, minimizing 99th percentile inference latency ratio, and minimizing model size ratio. Experiments on CICEVSE2024 and CICIDS2017 show that the proposed MOO-AutoML IDS achieves competitive weighted F1-scores, lower P99 inference latency, and smaller model sizes than the compared methods. Overall, the results indicate that the proposed method can support accurate and efficient intrusion detection for EVCS and IoT security under practical deployment constraints.
CommentsTo appear in the Proceedings of the 2026 IEEE Global Communications Conference (GLOBECOM 2026). Code is available at: https://github.com/LiYangHart/MOO-NSGA-III-AutoML-based-Intrusion-Detection-System
