{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:12:42Z","timestamp":1773155562657,"version":"3.50.1"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T00:00:00Z","timestamp":1743638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Network intrusion detection is a critical component of maintaining network security, especially as cyber threats become increasingly sophisticated. While deep learning-based intrusion detection algorithms have shown promise, they often struggle with high-dimensional datasets containing outliers, anomalies, or rare events. This study addresses these challenges by proposing a novel approach that combines the Improved Gravitational Search Algorithm (IGSA) with the Soft Actor-Critic (SAC) reinforcement learning algorithm, aiming to enhance detection accuracy and computational efficiency.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We introduce the IGSA-SAC intrusion detection model, which leverages an enhanced Gravitational Search Algorithm (IGSA) to improve robustness against outliers and dynamically adjust the exploration-exploitation balance. This is achieved through fitness normalization with an Adaptive Search Radius and a sigmoid function to modulate the gravitational constant. The IGSA-SAC method effectively navigates the search space to identify the most relevant features for intrusion detection, reducing dimensionality and computational complexity. Additionally, we design a reinforcement learning reward function to guide the learning process, encouraging the agent to improve detection effectiveness while minimizing false alarms and missed detections.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Experiments were conducted on the NSL-KDD and AWID datasets to evaluate the performance of IGSA-SAC. The results demonstrate that IGSA-SAC achieves an accuracy of 84.15% and an <jats:italic>F<\/jats:italic>1-score of 84.85% on the NSL-KDD dataset. On the AWID dataset, IGSA-SAC surpasses 98.9% in both accuracy and <jats:italic>F<\/jats:italic>1-score, outperforming existing intrusion detection algorithms.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The proposed IGSA-SAC method significantly improves intrusion detection performance by effectively handling high-dimensional datasets and reducing computational complexity. The results highlight the potential of IGSA-SAC as a robust and efficient solution for real-world network intrusion detection systems, offering enhanced accuracy and reliability in identifying cyber threats.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fcomp.2025.1574211","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T07:01:19Z","timestamp":1743663679000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["IGSA-SAC: a novel approach for intrusion detection using improved gravitational search algorithm and soft actor-critic"],"prefix":"10.3389","volume":"7","author":[{"given":"Lizhong","family":"Jin","sequence":"first","affiliation":[]},{"given":"Rulong","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Xiaoling","family":"Han","sequence":"additional","affiliation":[]},{"given":"Xueying","family":"Cui","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.aej.2024.01.073","article-title":"Optimizing intrusion detection using intelligent feature selection with machine learning model","volume":"91","author":"Aljehane","year":"2024","journal-title":"Alex. Eng. J."},{"key":"B2","doi-asserted-by":"publisher","first-page":"101322","DOI":"10.1016\/j.jestch.2022.101322","article-title":"A hybrid CNN+LSTM-based intrusion detection system for industrial IoT networks","volume":"38","author":"Altunay","year":"2023","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"B3","doi-asserted-by":"publisher","first-page":"103598","DOI":"10.1016\/j.cose.2023.103598","article-title":"Designing accurate lightweight intrusion detection systems for IoT networks using fine-tuned linear SVM and feature selectors","volume":"137","author":"Azimjonov","year":"2024","journal-title":"Comput. Secur."},{"key":"B4","doi-asserted-by":"publisher","first-page":"103485","DOI":"10.1016\/j.adhoc.2024.103485","article-title":"Optimizing feature selection in intrusion detection systems: Pareto dominance set approaches with mutual information and linear correlation","volume":"159","author":"Barbosa","year":"2024","journal-title":"Ad Hoc Netw."},{"key":"B5","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.procs.2016.06.016","article-title":"Performance evaluation of supervised machine learning algorithms for intrusion detection","volume":"89","author":"Belavagi","year":"2016","journal-title":"Proc. Comput. Sci."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.procs.2018.01.091","article-title":"Performance evaluation of intrusion detection based on machine learning using Apache Spark","volume":"127","author":"Belouch","year":"2018","journal-title":"Proc. Comput. Sci."},{"key":"B7","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.comnet.2019.05.013","article-title":"Adversarial environment reinforcement learning algorithm for intrusion detection","volume":"159","author":"Caminero","year":"2019","journal-title":"Comput. Netw."},{"key":"B8","doi-asserted-by":"publisher","first-page":"64761","DOI":"10.1109\/ACCESS.2022.3183597","article-title":"Pick quality over quantity: expert feature selection and data preprocessing for 802.11 intrusion detection systems","volume":"10","author":"Chatzoglou","year":"2022","journal-title":"IEEE Access"},{"key":"B9","doi-asserted-by":"publisher","first-page":"3014","DOI":"10.1016\/j.asoc.2012.04.020","article-title":"A hybrid network intrusion detection system using simplified swarm optimization (SSO)","volume":"12","author":"Chung","year":"2012","journal-title":"Appl. Soft Comput."},{"key":"B10","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.future.2022.01.026","article-title":"Imbalanced data classification: A KNN and generative adversarial networks-based hybrid approach for intrusion detection","volume":"131","author":"Ding","year":"2022","journal-title":"Future Gener. Comput. Syst."},{"key":"B11","doi-asserted-by":"publisher","first-page":"4197","DOI":"10.1109\/TNSM.2021.3120804","article-title":"Network abnormal traffic detection model based on semi-supervised deep reinforcement learning","volume":"18","author":"Dong","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Manage."},{"key":"B12","doi-asserted-by":"publisher","first-page":"100709","DOI":"10.1016\/j.iot.2023.100709","article-title":"An optimized CNN-based intrusion detection system for reducing risks in smart farming","volume":"22","author":"El-Ghamry","year":"2023","journal-title":"Internet Things"},{"key":"B13","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/SPW53761.2021.00009","article-title":"\u201cTroubleshooting an intrusion detection dataset: the CICIDS2017 case study,\u201d","volume-title":"2021 IEEE Security and Privacy Workshops (SPW)","author":"Engelen","year":"2021"},{"key":"B14","doi-asserted-by":"publisher","first-page":"103675","DOI":"10.1016\/j.cose.2023.103675","article-title":"A feature selection based on genetic algorithm for intrusion detection of industrial control systems","volume":"139","author":"Fang","year":"2024","journal-title":"Comput. Secur."},{"key":"B15","unstructured":"CICFlowMeter [Computer software]"},{"key":"B16","doi-asserted-by":"publisher","first-page":"102158","DOI":"10.1016\/j.cose.2020.102158","article-title":"An effective intrusion detection approach using SVM with na\u00efve Bayes feature embedding","volume":"103","author":"Gu","year":"2021","journal-title":"Comput. Secur."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv [Preprint]"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1016\/j.asoc.2007.10.007","article-title":"A distributed PSO\u2013SVM hybrid system with features selection and parameter optimization","volume":"8","author":"Huang","year":"2008","journal-title":"Appl. Soft Comput."},{"key":"B19","article-title":"\u201cApplication of quantum-inspired binary gravitational search algorithm for optimal power quality monitor placement,\u201d","author":"Ibrahim","year":"2012","journal-title":"Proceedings of the 11th WSEAS International Conference on Artificial Intelligence, Knowledge Engineering and Data Bases (AIKED \u201812)"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1109\/IEMDC.2011.5994627","article-title":"\u201cOptimal placement of power quality monitors in distribution systems using the topological monitor reach area,\u201d","volume-title":"Proceedings of the International Electric Machines and Drives Conference, Niagara Falls, Canada","author":"Ibrahim","year":""},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1109\/ICEEI.2011.6021845","article-title":"\u201cAn effective power quality monitor placement method utilizing quantum inspired particle swarm optimization,\u201d","volume-title":"Proceedings of the International Conference on Electrical Engineering and Informatics, Bandung, Indonesia","author":"Ibrahim","year":""},{"key":"B22","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1109\/COMST.2015.2402161","article-title":"Intrusion detection in 802.11 networks: empirical evaluation of threats and a public dataset","volume":"18","author":"Kolias","year":"2015","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835397","article-title":"An introduction to deep reinforcement learning","author":"Lavet","year":"2018","journal-title":"arXiv preprint"},{"key":"B24","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.enconman.2010.07.012","article-title":"Parameters identification of hydraulic turbine governing system using improved gravitational search algorithm","volume":"52","author":"Li","year":"2011","journal-title":"Energy Convers. Manage."},{"key":"B25","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1016\/S0167-4048(02)00514-X","article-title":"Use of K-Nearest Neighbor classifier for intrusion detection","volume":"21","author":"Liao","year":"2002","journal-title":"Comput. Secur."},{"key":"B26","doi-asserted-by":"publisher","first-page":"112963","DOI":"10.1016\/j.eswa.2019.112963","article-title":"Application of deep reinforcement learning to intrusion detection for supervised problems","volume":"141","author":"Lopez-Martin","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119030","article-title":"Dual-IDS: A bagging-based gradient boosting decision tree model for network anomaly intrusion detection system","author":"Louk","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"B28","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1109\/TNSE.2020.3004312","article-title":"AESMOTE: adversarial reinforcement learning with SMOTE for anomaly detection","volume":"8","author":"Ma","year":"2020","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"B29","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/j.asoc.2009.08.038","article-title":"Comprehensive learning particle swarm optimization for reactive power dispatch","volume":"10","author":"Mahadevan","year":"2010","journal-title":"Appl. Soft Comput."},{"key":"B30","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1109\/COMST.2018.2847722","article-title":"A detailed investigation and analysis of using machine learning techniques for intrusion detection","volume":"21","author":"Mishra","year":"2018","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"B31","doi-asserted-by":"publisher","first-page":"10770","DOI":"10.1016\/j.eswa.2011.01.129","article-title":"Modified genetic algorithms for manufacturing process planning in multiple parts manufacturing lines","volume":"38","author":"Musharavati","year":"2011","journal-title":"Expert Syst. Appl."},{"key":"B32","doi-asserted-by":"publisher","first-page":"100875","DOI":"10.1016\/j.measen.2023.100875","article-title":"Particle swarm optimization based artificial neural network (PSO-ANN) model for effective k-barrier count intrusion detection system in WSN","volume":"29","author":"Narayanan","year":"2023","journal-title":"Measure. Sens."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.05799","article-title":"Deep reinforcement learning for cybersecurity","author":"Nguyen","year":"2019","journal-title":"arXiv [Preprint]"},{"key":"B34","doi-asserted-by":"publisher","first-page":"7","DOI":"10.5120\/ijca2017915495","article-title":"A comparative study of categorical variable encoding techniques for neural network classifiers","volume":"175","author":"Potdar","year":"2017","journal-title":"Int. J. Comput. Appl."},{"key":"B35","doi-asserted-by":"publisher","first-page":"103751","DOI":"10.1016\/j.cose.2024.103751","article-title":"Archimedes Fire Hawk Optimization enabled feature selection with deep maxout for network intrusion detection","volume":"140","author":"Rani","year":"2024","journal-title":"Comput. Secur."},{"key":"B36","volume-title":"Gravitational search algorithm","author":"Rashedi","year":"2007"},{"key":"B37","article-title":"\u201cAllocation of static var compensator using gravitational search algorithm,\u201d in","author":"Rashedi","year":"2007","journal-title":"Proceedings of the First Joint Conference on Fuzzy and Intelligent Systems"},{"key":"B38","doi-asserted-by":"publisher","first-page":"2232","DOI":"10.1016\/j.ins.2009.03.004","article-title":"GSA: a gravitational search algorithm","volume":"179","author":"Rashedi","year":"2009","journal-title":"Inf. Sci."},{"key":"B39","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/s11047-009-9175-3","article-title":"BGSA: binary gravitational search algorithm","volume":"9","author":"Rashedi","year":"2010","journal-title":"Nat. Comput."},{"key":"B40","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.jer.2023.100122","article-title":"Enhancing intrusion detection in IoT systems: a hybrid metaheuristics-deep learning approach with ensemble of recurrent neural networks","volume":"11","author":"Sanju","year":"2023","journal-title":"J. Eng. Res."},{"key":"B41","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1016\/j.scient.2011.04.003","article-title":"Disruption, a new operator in gravitational search algorithm","volume":"18","author":"Sarafrazi","year":"2011","journal-title":"Scientia Iranica"},{"key":"B42","doi-asserted-by":"publisher","first-page":"103483","DOI":"10.1016\/j.cose.2023.103483","article-title":"RAIDS: Robust autoencoder-based intrusion detection system model against adversarial attacks","volume":"135","author":"Sarikaya","year":"2023","journal-title":"Comput. Secur."},{"key":"B43","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.patrec.2022.08.008","article-title":"Detection of intrusion behavior in cloud applications using Pearson's chi-squared distribution and decision tree classifiers","volume":"162","author":"Sathish","year":"2022","journal-title":"Pattern Recognit. Lett."},{"key":"B44","doi-asserted-by":"publisher","first-page":"102923","DOI":"10.1016\/j.jisa.2021.102923","article-title":"Attention based multi-agent intrusion detection systems using reinforcement learning","volume":"61","author":"Sethi","year":"2021","journal-title":"J. Inf. Secur. Appl."},{"key":"B45","doi-asserted-by":"publisher","first-page":"109960","DOI":"10.1016\/j.asoc.2022.109960","article-title":"Intrusion detection model using gene expression programming to optimize parameters of convolutional neural network for energy internet","volume":"134","author":"Song","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"B46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CISDA.2009.5356528","article-title":"\u201cA detailed analysis of the KDD CUP 99 data set,\u201d","volume-title":"2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications","author":"Tavallaee","year":"2009"},{"key":"B47","doi-asserted-by":"publisher","first-page":"103608","DOI":"10.1016\/j.jisa.2023.103608","article-title":"Federated reinforcement learning based intrusion detection system using dynamic attention mechanism","volume":"78","author":"Vadigi","year":"2023","journal-title":"J. Inf. Secur. Appl."},{"key":"B48","doi-asserted-by":"publisher","first-page":"41525","DOI":"10.1109\/ACCESS.2019.2895334","article-title":"Deep learning approach for intelligent intrusion detection system","volume":"7","author":"Vinayakumar","year":"2019","journal-title":"IEEE Access"},{"key":"B49","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.knosys.2017.09.014","article-title":"An effective intrusion detection framework based on SVM with feature augmentation","volume":"136","author":"Wang","year":"2017","journal-title":"Knowl. Based Syst."},{"key":"B50","doi-asserted-by":"publisher","first-page":"123014","DOI":"10.1016\/j.eswa.2023.123014","article-title":"An intrusion detection algorithm based on joint symmetric uncertainty and hyperparameter optimized fusion neural network","volume":"244","author":"Wang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"B51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2018\/8738613","article-title":"A survey on machine learning-based mobile big data analysis: challenges and applications","volume":"2018","author":"Xie","year":"2018","journal-title":"Wireless Commun. Mobile Comput."},{"key":"B52","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/4235.771163","article-title":"Evolutionary programming made faster","volume":"3","author":"Yao","year":"1999","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"B53","doi-asserted-by":"publisher","first-page":"2513","DOI":"10.1016\/j.ifacol.2020.12.226","article-title":"Intrusion detection of industrial control system based on double-layer one-class support vector machine","volume":"53","author":"Zhang","year":"2020","journal-title":"IFAC-PapersOnLine"},{"key":"B54","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.knosys.2016.10.030","article-title":"An improved NSGA-III algorithm for feature selection used in intrusion detection","volume":"116","author":"Zhu","year":"2017","journal-title":"Knowl. Based Syst."}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1574211\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T07:02:18Z","timestamp":1743663738000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1574211\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,3]]},"references-count":54,"alternative-id":["10.3389\/fcomp.2025.1574211"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2025.1574211","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,3]]},"article-number":"1574211"}}