Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey
Open accessThe DOI matches its Crossref record; 87 of the 89 references it cites were found in a registry or an index.
Abstract
Networks play important roles in modern life, and cyber security has become a vital research area. An intrusion detection system (IDS) which is an important cyber security technique, monitors the state of software and hardware running in the network. Despite decades of development, existing IDSs still face challenges in improving the detection accuracy, reducing the false alarm rate and detecting unknown attacks. To solve the above problems, many researchers have focused on developing IDSs that capitalize on machine learning methods. Machine learning methods can automatically discover the essential differences between normal data and abnormal data with high accuracy. In addition, machine learning methods have strong generalizability, so they are also able to detect unknown attacks. Deep learning is a branch of machine learning, whose performance is remarkable and has become a research hotspot. This survey proposes a taxonomy of IDS that takes data objects as the main dimension to classify and summarize machine learning-based and deep learning-based IDS literature. We believe that this type of taxonomy framework is fit for cyber security researchers. The survey first clarifies the concept and taxonomy of IDSs. Then, the machine learning algorithms frequently used in IDSs, metrics, and benchmark datasets are introduced. Next, combined with the representative literature, we take the proposed taxonomic system as a baseline and explain how to solve key IDS issues with machine learning and deep learning techniques. Finally, challenges and future developments are discussed by reviewing recent representative studies.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“The LSTM model was proposed by Hochreiter and Schmidhuber in 1997 [29].”
BackgroundMethodA Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“RNNs are networks designed for sequential data and are widely used in natural language processing (NLP) [26–28].”
Background"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 1×
“Training a DBN involves two stages: unsupervised pretraining and supervised fine-tuning [18,19].”
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 2×
“To solve the long-term dependence problem, many RNN variants have been proposed, such as long short-term memory (LSTM) [29], gated recurrent unit (GRU) [30], and bi-RNN [31].”
BackgroundMethodBidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 1×
“To solve the long-term dependence problem, many RNN variants have been proposed, such as long short-term memory (LSTM) [29], gated recurrent unit (GRU) [30], and bi-RNN [31].”
BackgroundSpeech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“RNNs are networks designed for sequential data and are widely used in natural language processing (NLP) [26–28].”
BackgroundExtracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · cited 1×
“Many famous autoencoder variants exist, such as denoising autoencoders [14,15] and sparse autoencoders [16].”
Background
Research works printed but not linked: 2
- Zhang, H., Yu, X., Ren, P., Luo, C., and Min, G. (2019). Deep Adversarial Learning in Intrusion Detection: A Data Augmentation Enhanced Framework. arXiv.
- Radford, B.J., Apolonio, L.M., Trias, A.J., and Simpson, J.A. (2018). Network traffic anomaly detection using recurrent neural networks. arXiv.
Cited by
Items 601–700 of 1,000
An Efficient Network Attack Detection System Using Recurrent Neural Network Models
Amogh, M., Shaikh, A., Baraker, N., Baligar, D., & Patil, P. C. (2024) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet61516.2024.10593098 · Cited by 5
“This study explores strategies for detecting network attacks [6], emphasizing the efficacy of deep learning methodologies.”
BackgroundTIBS: A Deep-Learning Model for Network Intrusion Detection for SDN Environments
Zhang, Y., Wu, X., & Dong, H. (2024) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs61882.2024.10603223 · Cited by 5
A study on Anomaly-based Intrusion Detection Systems Employing Supervised Deep Learning Techniques
Shaffi, A. S., Chacko, J. V., Eliyan, G., & Balaji, S. (2024) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc62624.2024.00069 · Cited by 5
“For each and every variant in the IT sector needs a different types of security solutions [1].”
BackgroundFast Anomalous Traffic Detection System for Secure Vehicular Communications
Al-Haija, Q. S. A., & Alsulami, A. A. (2024) · Intelligent and Converged Networks · doi:10.23919/icn.2024.0021 · Cited by 6
Presekal, A., Stefanov, A. I., Rajkumar, V. S., & Pálenský, P. (2025) · Wiley eBooks · doi:10.1002/9781394191529.ch19 · Cited by 8
Adversarial Sample Generation Based on Model Simulation Analysis in Intrusion Detection Systems
Sun, J., & Yang, S. (2025) · Electronics · doi:10.3390/electronics14050870 · Cited by 5
“They can accurately identify known attacks while also detecting some unknown attacks, thereby reducing false positives and missed detections [1].”
A case study on the representativeness of public DoS network traffic data for cybersecurity research
Catillo, M., Pecchia, A., Rak, M., & Villano, U. (2020) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3407023.3407042 · Cited by 5
“More recently, with the rapid expansion of deep learning, many DoS detectors have spread in the literature [13]; noteworthy, some of these detectors achieve a detection rate close to 100% in some cases.”
BackgroundTrusted Security Model for IDS Using Deep Learning
Makdi, K. A., Sheldon, F. T., & Abuhussein, A. (2020) · International Conference on Signal Processing and Information Security (ICSPIS) · doi:10.1109/icspis51252.2020.9340136 · Cited by 5
“[29] Moreover, the layered and thin structures of sequential deep learning models make them be the perfect match for use than low-powered and resource-constrained devices while ensuring real-time detection of anomalies .”
BackgroundIntrusion Detection using Deep Neural Network Algorithm on the Internet of Things
Ikhwan, S., Wibowo, A., & Warsito, B. (2022) · IEEE International Conference on Communication, Networks and Satellite (COMNETSAT) · doi:10.1109/comnetsat56033.2022.9994499 · Cited by 5
“Various machine learning methods are then used to improve the IDS's ability to detect known and unknown attacks [4].”
MethodA novel cyber intrusion detection model based on improved hybrid sampling
Qian, H., Zhang, X., Zhang, C., & Jiang, C. (2023) · Transactions of the Institute of Measurement and Control · doi:10.1177/01423312231158422 · Cited by 5
“Each loop contains a forget gate, an input gate, an output gate and a select gate (Liu and Lang, 2019; Zhu et al., 2019).”
BackgroundJilcha, L. A., Kim, D.-H., Jang‐Jaccard, J., & Kwak, J. (2023) · Computer Systems Science and Engineering · doi:10.32604/csse.2023.037615 · Cited by 5
Anomaly Detection - Recent Advances, AI and ML Perspectives and Applications
Krishna Parimala, V. (2023) · Artificial intelligence · doi:10.5772/intechopen.110988 · Cited by 6
An Intelligent Approach for Intrusion Detection using Snake Optimizer and Random Forest
Duraibi, S. (2022) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci58124.2022.00180 · Cited by 5
“ML approaches for ID gained special attention because of its ability to use hundreds of features for classifying normal system behavior and attack attempts [7, 8].”
BackgroundDemystifying Intrusion Detection Process using Machine Learning Techniques
Hemraj, Sonia, S., Ashish, Gupta, G., Rana, A., & Gupta, A. (2024) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom61295.2024.10499111 · Cited by 5
“Additionally, the most typical task in supervised learning is classification [24].”
BackgroundPrediction of Intrusion Detection in Voice over Internet Protocol System using Machine Learning
Choti, C., Hnoohom, N., Tritilanunt, S., & Yuenyong, S. (2021) · International Conference on Computer and Communications Management (ICCCM) · doi:10.1145/3479162.3479185 · Cited by 5
“The research purpose records the data of intrusion detection in VoIP telephony system for classifying the data using machine learning algorithms [5].”
MethodDarley, O. G., Adenowo, A. A., & Yussuff, A. I. O. (2022) · FUOYE Journal of Engineering and Technology · doi:10.46792/fuoyejet.v7i2.802 · Cited by 6
“Liu and Lang (2019) presented a taxonomy of IDS that take data objects to classify and summarize MLand DL-based IDS literature.”
BackgroundA Lightweight DoS and DDoS Attack Detection Mechanism-Based on Deep Learning
Satpathy, S. P., Mohanty, S., & Kumar, R. (2022) · International Conference on Computational Intelligence and Networks (CINE) · doi:10.1109/cine56307.2022.10037402 · Cited by 5
“Helpnet Security has analysed the DDoS attacks for 2020 and 2021, and the data shows the increase in DDoS attacks [1]–[3].”
BackgroundStill Rings Movements Recognition in Gymnastics Sport Based on Deep Learning
Abdullah, A. S., & Alsaif, K. (2023) · Wasit Journal of Pure sciences · doi:10.31185/wjps.123 · Cited by 5
“Taking into account the accessible handling power and memory, as well as late headways in registering power and memory limit, it is currently doable to prepare huge organizations effectively[11-12].”
BackgroundA Survey on Supervised Machine Learning in Intrusion Detection Systems for Internet of Things
Saidin, S. B., & Hisham, S. B. I. (2023) · International Conference on Software Engineering and Computer Systems · doi:10.1109/icsecs58457.2023.10256275 · Cited by 5
A HITL-Integrated Machine Learning Approach to Secure Drone Networks for IIoT Applications
Zeng, Q., Naït‐Abdesselam, F., & Chen, Z. (2023) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps58843.2023.10465098 · Cited by 6
“Several studies have explored the use of ML techniques for intrusion detection in various domains, including computer networks, IoT devices, and industrial control systems [11].”
BackgroundKhamis, R. A. (2020) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2020-14257 · Cited by 6
Ghadi, Y. Y., Talpur, D. B., Mazhar, T., Irfan, H. M., Salaria, U. A., Hanif, S., Shahzad, T., & Hamam, H. (2023) · Research Square · doi:10.21203/rs.3.rs-3381005/v1 · Cited by 5
Machine learning in food authentication: A sustainable solution to global food challenges
Malik, M., & Dewan, A. (2025) · Letters in Food Research · doi:10.26656/lifr.1.e25050 · Cited by 4
Wang, X., Ma, L., Das, S. K., & Liu, Z. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3565257 · Cited by 4
“Many methods have been proposed, including machine learning approaches, which enable models to automatically learn sample features and detect unknown attacks [12].”
Srivastav, N., & Singh, R. K. (2025) · SN Computer Science · doi:10.1007/s42979-025-04336-z · Cited by 4
“Different Machine learning algorithms [ 48– 50 ] are used for multiclass classification.”
AI-Powered Cybersecurity: A Technical Review of Intrusion Detection Models, Tools, and Metrics
Badawy, W. (2025) · International Telecommunications Conference (ITC-Egypt) · doi:10.1109/itc-egypt66095.2025.11186688 · Cited by 4
“Consequently, IDS trained on these datasets may perform well in lab conditions but poorly in deployment [11].”
InfluentialAdvancing Machine Learning Strategies for Power Consumption-Based IoT Botnet Detection
Wakili, A. A., Guni, S., Khan, S. A., Yu, W., & Jung, W. (2025) · Sensors · doi:10.3390/s25247553 · Cited by 6
“As systems became more complex, researchers began applying machine learning (ML) and deep learning (DL) techniques to IDSs, offering dynamic threat modeling and adaptive anomaly detection capabilities [2,7–12].”
Danang, D., & Mustofa, Z. (2026) · Journal of Artificial Intelligence and Technology · doi:10.37965/jait.2025.0887 · Cited by 14
“Reference [2] stated that misclassi fi cation due to low attack detection accuracy and the inability to identify modern attacks are the main focus of IDS.”
Lightweight Protection Mechanisms for IoT Networks Based on Trust Modelling
Rodríguez, A., López‐Chau, A., Dávila-Nicanor, L., Landassuri-Moreno, V. M., & Lazcano-Salas, S. (2026) · IoT · doi:10.3390/iot7010018 · Cited by 4
“On the other hand, Generative Adversarial Networks (GANs) are currently used for data augmentation and intrusion detection [52,53].”
García, P., de Curtò, J., & de Zarzà, I. (2025) · International Conference on Foundation and Large Language Models (FLLM) · doi:10.1109/fllm67465.2025.11391169 · Cited by 6
“Despite the prevalence of tree-based models, recent advances in deep learning have catalyzed interest in neural approaches for structured cybersecurity data [15], [16].”
A Novel Approach based on Improved Naive Bayes for 5G Air Interface DDoS Detection
Peng, C., Fan, W., Huang, W., & Zhu, D. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10118854 · Cited by 4
“At present, commonly used classification algorithms for attack detection include: support vector machine (SVM), decision tree classification, K-nearest neighbor (KNN) classification, naive Bayes classification, machine learning, etc. [6-9].”
MethodA Multivariate Machine Learning Model of Adsorptive Lindane Removal from Contaminated Water
Akinpelu, A. A., Nazal, M. K., Shafiullah, M., Islam, M. K., Islam, M. M., Rahman, A., Rahman, S. M., & Rahman, M. M. (2023) · Applied Sciences · doi:10.3390/app13127086 · Cited by 4
Zhang, J., & Qi, H. (2023) · Soft Computing · doi:10.1007/s00500-023-08803-8 · Cited by 4
RetractedPrediction Model based on Iris Dataset Via Some Machine Learning Algorithms
Aziz, C. F., & Awrahman, B. J. (2023) · Journal of Kufa for Mathematics and Computer · doi:10.31642/jokmc/2018/100210 · Cited by 4
“…algorithms and methods for Machine Learning, Basically, machine learning is the process of causing the machine to make the same decisions as the human brain. machine learning which is the main part of artificial intelligence has two main categories[2]supervised learning and unsupervised learning.”
MethodMachine Learning-Based E-Learners’ Engagement Level Prediction Using Benchmark Datasets
Theophilus, G., & Eke, C. I. (2023) · International Journal of Applied Information Systems · doi:10.5120/ijais2023451951 · Cited by 6
An Effective Anomaly Detection Approach based on Hybrid Unsupervised Learning Technologies in NIDS
Kim, K. (2024) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2024.02.012 · Cited by 4
A Review Paper: Security for Supervisory Control and Data Acquisition SCADA Based on DNP3
Jasim, A. A., & Alheeti, K. M. A. (2023) · International Conference on Developments in eSystems Engineering (DeSE) · doi:10.1109/dese60595.2023.10469230 · Cited by 4
“…over decades, yet there are still issues with enhancing detection accuracy .for identifying unanticipated assaults and lowering false alarm rates[36] V. LITERATURE SURVEY This section showcases recent developments in SCADA /ICS/DNP3-based systems: J. Bai et al. [37] proposed a network-based…”
BackgroundPathak, M. (2024) · Journal of Electrical Systems · doi:10.52783/jes.762 · Cited by 4
Perancangan Sistem Deteksi Objek Pada Robot Transporter Menggunakan Metode Darknet YOLOv8
Yudha, Y. F., Aditya, A. A. Y., Rasyid, R. A. Y., Indra, N. I. A., & Melati, M. W. W. (2024) · Electrician Jurnal Rekayasa dan Teknologi Elektro · doi:10.23960/elc.v18n2.2595 · Cited by 4
Botnet Detection in Distributed Network Using Machine Learning- A Detailed Review
Jain, R., & Nihalani, N. (2024) · International Conference on Communication, Computer Sciences and Engineering (IC3SE) · doi:10.1109/ic3se62002.2024.10593476 · Cited by 4
“Zaheer et al. [35] addresses the increasing threat of botnet attacks on computer networks by proposing a hybrid machine-learning model.”
BackgroundChen, S., Chen, Y., & Feng, M. (2024) · Sensors · doi:10.3390/s24165393 · Cited by 4
“The new algorithm combines the powerful global search capability of the genetic algorithm and the efficient local search capability of the gray wolf optimization algorithm, thus effectively avoiding the problem of locally optimal solutions during the iteration process [33–36].”
MethodGenerative AI for Threat Hunting and Behaviour Analysis
Sindiramutty, S. R., Jhanjhi, N. Z., Akbar, R., Hussain, M., Ray, S. K., & Amsaad, F. (2024) · Advances in digital crime, forensics, and cyber terrorism book series · doi:10.4018/979-8-3693-8944-7.ch007 · Cited by 5
Güngör, O., Rosing, T., & Akşanlı, B. (2024) · IEEE International Conference on Cyber Security and Resilience (CSR) · doi:10.1109/csr61664.2024.10679458 · Cited by 5
“Support vector machine, random forest, and deep neural networks are some ML methods proposed in the literature [4].”
BackgroundMethodA Deep Learning Approach to Detect Cross-Site Scripting Attack as a Web Application Firewall
Sa'adah, K., Hanaputra, R. R., Girinoto, & Cahyono, S. (2024) · International Conference on Information Technology and Computing (ICITCOM) · doi:10.1109/icitcom62788.2024.10762471 · Cited by 4
Comparative Study: Flower Classification using Deep Learning, SMOTE and Fine-Tuning
Praskatama, V., Shidik, G. F., & Ningrum, A. P. (2024) · Journal of Applied Informatics and Computing · doi:10.30871/jaic.v8i2.8730 · Cited by 5
Naseera, F., & N., J. (2025) · Journal of Information Technology and Digital World · doi:10.36548/jitdw.2025.1.003 · Cited by 4
Network Intrusion Detection with Nonsymmetric Deep Autoencoding Feature Extraction
Gu, Z., Wang, L., Liu, C., & Wang, Z. (2021) · Security and Communication Networks · doi:10.1155/2021/2843856 · Cited by 5
“Meanwhile, for the CIC-IDS dataset, the dimension of the input data is dropped from 78 to 24, while c1 and c2 are set to 14 and 24, respectively.”
MethodInfluentialIntrusion Detection System(IDS) Analysis Using ML
Dutta, R., Nirupama, B. K., & Niranjanamurthy (2022) · IEEE Mysore Sub Section International Conference (MysuruCon) · doi:10.1109/mysurucon55714.2022.9972442 · Cited by 4
“In order to organize and summarise the IDS literature based on ML and deep learning, this study[6] presents an IDS taxonomy that leverages data objects as the major dimension.”
MethodIntrusion Detection System Using Initialization-based Few-shot Learning
Haruna, B., Ibrahim, N. M., & Boukar, M. M. (2023) · International Conference on Multidisciplinary Engineering and Applied Science (ICMEAS) · doi:10.1109/icmeas58693.2023.10379422 · Cited by 4
“The data used in this study was derived from data that was already generated by [5][6], and it incorporates findings from various ML and DL models that were applied to the IDS.”
BackgroundMethodEvolving Threats and AI Solutions for Modern Hybrid Cloud Architectures
Anjani, C., Balajee, R. M., Divya, G., Sree, Y. S., Padmanabham, K., & Srithar, S. (2023) · International Conference on Automation, Computing and Renewable Systems (ICACRS) · doi:10.1109/icacrs58579.2023.10404167 · Cited by 4
Sun, Y., Wei, Y., Zhang, Y., & Zhao, J. L. (2025) · Applied Optics · doi:10.1364/ao.547280 · Cited by 4
Amiri, A., Ghaffarnia, A., Sakib, S. K., Wu, D., & Liang, Y. (2025) · IEEE International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic63015.2025.10848591 · Cited by 4
Arvind, T. K. R. (2020) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2020.30598 · Cited by 4
Leveraging LSTM-RNN combined with SVM for Network Intrusion Detection
Patidar, S., Tripathi, M., & Gupta, S. K. (2021) · International Conference on Data Science, Machine Learning and Artificial Intelligence (DSMLAI) · doi:10.1145/3484824.3484908 · Cited by 4
“…, recurrent neural network, genetic algorithms, Self OrganizingMaps (SOM) and support vector machine etc., have shown optimal performance in detecting known and unknown intrusions either at host-side or in a network by analyzing the network traffic and the patterns occurring in the traffic[7].”
BackgroundBlock Ciphers Analysis Based on a Fully Connected Neural Network
Alwan, A. H., & Kashmar, A. H. (2023) · Ibn AL- Haitham Journal For Pure and Applied Science · doi:10.30526/36.1.3058 · Cited by 4
A Review of Benchmark Datasets and its Impact on Network Intrusion Detection Techniques
Haripriya, C., & Jagadeesh, P. (2022) · International Conference on Cognitive Computing and Information Processing · doi:10.1109/ccip57447.2022.10058660 · Cited by 4
“The main advantage of using hybrid approach is, it combines both misuse and anomaly detection [5].”
BackgroundMachine Learning Techniques in Intrusion Detection System: A Survey
Khandait, R., Chourasia, U., & Dixit, P. (2023) · Algorithms for intelligent systems · doi:10.1007/978-981-19-7892-0_28 · Cited by 4
eMinD: Efficient and Micro-Flow Independent Detection of Distributed Network Attacks
Kopmann, S., & Zitterbart, M. (2023) · International Conference on the Network of the Future (NOF) · doi:10.1109/nof58724.2023.10302763 · Cited by 4
Pucoe, G., & Obagbuwa, I. C. (2024) · International Conference on Science, Engineering and Business for Driving Sustainable Development Goals (SEB4SDG) · doi:10.1109/seb4sdg60871.2024.10629839 · Cited by 4
“Deep learning generates more robust models, even when combining machine learning system of measurement [37].”
MethodKumar, K., Kumar, A., Kumar, V., & Kumar, S. (2021) · International Journal of Organizational and Collective Intelligence · doi:10.4018/ijoci.2022010102 · Cited by 4
WITHDRAWN: Real-Time Monitoring Of Big Data Sports Teaching Data Based On Complex Embedded System
Xie, X. (2022) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2021.104181 · Cited by 6
RetractedAbadeer, M., Ebeid, F. M. M., & Gorlatch, S. P. (2022) · Asia Symposium on Signal Processing (ASSP) · doi:10.1109/assp57481.2022.00020 · Cited by 5
“There are two main types of ML approaches, supervised learning and unsupervised learning [8].”
BackgroundDesign and Analysis of Intrusion Detection Using Deep Learning Models
Modak, A., & Dehalwar, V. (2024) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct62155.2024.10677142 · Cited by 3
“An effective IDS must detect known and unknown attack vectors, strengthening organizational defence against developing cyber threats [3, 4].”
BackgroundKomalasari, R. (2024) · Advances in information security, privacy, and ethics book series · doi:10.4018/979-8-3693-2223-9.ch006 · Cited by 3
Threat Modeling for Honeypot Deployment
Silaen, K. E., Gaol, F. L., Supangkat, S. H., & Ranti, B. (2024) · IEEE Information Technology International Seminar (ITIS) · doi:10.1109/itis64716.2024.10845226 · Cited by 3
Anugraha, M., Ebenezer, S. S., & Maheswari, S. (2025) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2025.102079 · Cited by 3
A HYBRID CNN-LSTM AND ADABOOST MODEL FOR CLASSIFYING INTRUSION IN IoT NETWORKS
Eguavoen, V. O., Olanrewaju, B. S., & Okafor, C. N. (2025) · FUDMA Journal of Sciences · doi:10.33003/fjs-2025-0905-3495 · Cited by 5
Dhanabal, S., Goswami, C., Praveen, R., & Vetriselvi, T. (2025) · Wireless Networks · doi:10.1007/s11276-025-03965-9 · Cited by 3
“One notable characteristic of DL is the deep structure that consists of multiple hidden layers [10] thereby providing incredible performance.”
Spiking Residual ShuffleNet-Based Intrusion Detection in IoT Environment
Jacob, S. L., & Sultana, H. P. (2025) · IEEE Access · doi:10.1109/access.2025.3579777 · Cited by 3
“The most commonly utilized ML approaches are ANN, Naive-Bayesian (NB), Support Vector Machines (SVM) [23], Self-Organized Maps, and Random Forests (RF).”
Shi, K., Ding, P., & Wang, J. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07534-x · Cited by 3
“By training models with a large number of normal and abnormal traffic samples, they aim to identify network attack traffic effectively [3–6].”
Shamsuzzaman, H. M., Mosleuzzaman, M., & Paran, M. S. (2025) · American Journal of Advanced Technology and Engineering Solutions · doi:10.63125/g937f918 · Cited by 3
“This extends the conclusions of Liu and Lang ( 2019) and Antoniali and Tonello (2014), who discussed protocol-specific vulnerabilities but lacked empirical data on comprehensive defense compatibility.”
Addressing IoT Security Challenges through Advanced Machine Learning and Encryption
Zainuddin, A. A., Anuar, A. A. K., Halim, A. A. A., & Rina, D. R. D. (2025) · Journal of Informatics and Web Engineering · doi:10.33093/jiwe.2025.4.3.9 · Cited by 3
IDS-IoT: Intrusion Detection System for the Internet of Things Using Enhanced Long-Short Term Memory
Meena, G., & Indian, A. (2025) · Artificial Intelligence and Applications · doi:10.47852/aiabonview52025066 · Cited by 10
“Researchers have created IDSs [33] that use ML techniques to overcome these problems.”
Moghaddasi, K., Rajabi, S., & Hosseinzadeh, M. (2025) · Wireless Personal Communications · doi:10.1007/s11277-025-11846-9 · Cited by 4
Resilient cybersecurity: ensemble deep learning and reinforcement learning for Next-Gen IDS
Kalpani, N., Rodrigo, N., Seneviratne, D., Ariyadasa, S. N., & Senanayake, J. (2026) · Iran Journal of Computer Science · doi:10.1007/s42044-025-00364-3 · Cited by 3
“ML-based approaches have addressed these limitations by learning patterns and behaviours from data, making them capable of identifying both known and unknown intrusions [14].”
Data Science and Machine Learning for Cyber Intrusion Detection: A Systematic Review
Ren, Y. (2026) · Machine Learning Research · doi:10.11648/j.mlr.20261101.12 · Cited by 5
Vallabhaneni, S. A. V. R. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i9s.9486 · Cited by 3
Network based Intrusion Detection using Time aware LSTM Autoencoder
Ratti, R., Singh, S. R., & Nandi, S. (2023) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom60117.2023.00359 · Cited by 3
“As also reported in the earlier studies [17], some of the concerns with supervised (signature-based) approach are - it not only requires labeled data but also fails to identify new types of attacks and zero-day attacks.”
ResultPham, T., Bui, H. N., Nguyen, M., Le, T. N., Vu, V., Pham, Q., & Quan, T. (2024) · Energy Reports · doi:10.1016/j.egyr.2024.10.048 · Cited by 3
Deokar, T. V., Shinde, J. N., & Sairise, R. M. (2024) · ShodhKosh Journal of Visual and Performing Arts · doi:10.29121/shodhkosh.v5.i6.2024.4825 · Cited by 3
GateIDS: A Single Network Architecture for Attack Detection and Multi-Class Classification
Youm, S., & Shin, K.-S. (2025) · IEEE Access · doi:10.1109/access.2025.3564068 · Cited by 3
“The advent of deep learning (DL) has significantly enhanced IDS capabilities by enabling the modeling of complex traffic patterns [4].”
Web-Based Attacks Detection Using Deep Learning Techniques: A Comprehensive Review
Alghofaili, L. N., & Ibrahim, D. M. (2025) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v39.i1.pp466-484 · Cited by 3
“In the context of web-based attack detection, datasets are required for neural network training and evaluation whereas some previous approaches select more than one dataset or create their own dataset [49].”
Chou, F.-I., Ho, W., Chen, Y. J., Tsai, J., & Chang, C.-W. (2020) · Applied Sciences · doi:10.3390/app10051566 · Cited by 3
“IDS is normally divided into anomaly, misuse, and hybrid detections [1,15].”
BackgroundIntrusion Detection in the Internet of Things
Bamou, A. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/0191.52020 · Cited by 3
“The following table 1 presents the advantages and disadvantages of each technique [31].”
MethodThinh, T. N., Bao, T. H. Q., Ngo, D., & Pham‐Quoc, C. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6370 · Cited by 3
Deep Learning Framework for Cybersecurity: Framework, Applications, and Future Research Trends
Singh, R. V., Bhushan, B., & Tyagi, A. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-33-4367-2_80 · Cited by 3
Prabu, S., Padmanabhan, J., & Bala, G. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-16-2422-3_23 · Cited by 3
Evaluation of the IP Identification Covert Channel Anomalies Using Support Vector Machine
Shehab, M., Korany, N. O., & Sadek, N. M. (2021) · IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD) · doi:10.1109/camad52502.2021.9617790 · Cited by 3
Comprehensive Composition to Spot Intrusions by Optimized Gaussian Kernel SVM
Kumar, K. (2022) · International Journal of Knowledge-Based Organizations · doi:10.4018/ijkbo.291689 · Cited by 3
Empirical Analysis of Machine Learning Models towards Adaptive Network Intrusion Detection Systems
Senthilkumar, S. P., & Arivarasan, A. (2022) · International Conference on Smart Systems and Inventive Technology (ICSSIT) · doi:10.1109/icssit53264.2022.9716526 · Cited by 3
An Efficient Intelligent Intrusion Detection System for Internet of Things
Abdaljabar, Z. H., Osman Nuri, U. C. A. N., & Alheeti, K. M. A. (2021) · International Conference on Developments in eSystems Engineering (DeSE) · doi:10.1109/dese54285.2021.9719551 · Cited by 3
Deep Learning Techniques for Anomaly based Intrusion Detection System: A Survey
Kumar, Y., Chouhan, L., & Subba, B. (2021) · International Conference on Computational Performance Evaluation (ComPE) · doi:10.1109/compe53109.2021.9751909 · Cited by 3
Bat-Inspired Optimization for Intrusion Detection Using an Ensemble Forecasting Method
Babu, R. A., & Kannan, S. (2022) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2022.024098 · Cited by 3
“Redundant and unrelated features may decrease the efficiency of the IDS, producing uninterpretable results [16].”
BackgroundImproved training of deep convolutional networks via minimum-variance regularized adaptive sampling
Rojas‐Domínguez, A., Valdez, S. I., Ornelas-Rodríguez, M., & Carpio, M. (2022) · Soft Computing · doi:10.1007/s00500-022-07131-7 · Cited by 3
“2020), security (Liu and Lang 2019), activity recognition (Thakur and Biswas 2020), biometrics (Choudhary et al.”
BackgroundAssessment of Network Intrusion Detection System Based on Shallow and Deep Learning Approaches
Meena, G., Babita, B., & Mohbey, K. K. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-07012-9_28 · Cited by 3
From Machine Learning Based Intrusion Detection to Cost Sensitive Intrusion Response
Hussain, T., Beard, A., Chen, L., Nugent, C., Liu, J., & Moore, A. (2022) · International Conference on Cryptography, Security and Privacy (CSP) · doi:10.1109/csp55486.2022.00031 · Cited by 5
A Brief Analysis on Machine Learning Classifiers for Intrusion Detection to Enhance Network Security
Mande, S., Ramachandran, N., Kumar, C. K., & Priyanka, C. N. (2022) · International Conference on Automation, Computing and Renewable Systems (ICACRS) · doi:10.1109/icacrs55517.2022.10029091 · Cited by 3
Multi-input MLP and LSTM-Based Neural Network Model for SQL Injection Detection
Sharma, V., & Kumar, S. (2023) · Algorithms for intelligent systems · doi:10.1007/978-981-19-7892-0_35 · Cited by 2
Comparison of Advanced Classification Algorithms Based Intrusion Detection from Real-Time Dataset
Aswanandini, R., & Deepa, C. (2023) · Automatic Control and Computer Sciences · doi:10.3103/s0146411623030021 · Cited by 3
de Souza, C. P., Westphall, C. B., & Machado, R. B. (2023) · doi:10.5753/sbc.12043.1.3 · Cited by 5
Metadata
- Authors
- Liu, H., & Lang, B.
- Affiliations
- State Key Laboratory of Software Development Environment (CN)
- Corresponding author
- Liu, Hongyu
- ORCID
- Lang, Bo
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2019-10-17
- Volume
- 9
- Issue
- 20
- Pages
- 4396
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W2980576170
- Cited by
- 1,133
- References
- 89
- Citations by year
- 2026: 124 · 2025: 204 · 2024: 247 · 2023: 223 · 2022: 176 · 2021: 114 · 2020: 44 · 2019: 1
- FWCI
- 45.82
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Hardware and Architecture › Network Packet Processing and Optimization
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Immune Systems Applications
- Keywords
- intrusion detection systems, machine learning, deep learning, network security, cybersecurity, false alarm reduction, unknown attack detection, benchmark dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.