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 301–400 of 1,000
Neto, H. N. C., Dusparić, I., Mattos, D. M. F., & Fernande, N. C. (2022) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft54395.2022.9844024 · Cited by 25
Flexible and Robust Real-Time Intrusion Detection Systems to Network Dynamics
Yu, K., Nguyen, K., & Park, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3199375 · Cited by 25
“Machine learning (ML) and deep learning (DL) techniques 118 have been popularly adapted to develop intrusion detection 119 systems (IDS) because of their high accuracy, automation, 120 and no previous knowledge requirement [1], [2], [3], [4], [7], 121 [8], [9], [10], [17].”
BackgroundMethodAlasmari, S. M., Sakly, H., Kraïem, N., & Algarni, A. D. (2025) · Discover Internet of Things · doi:10.1007/s43926-025-00202-9 · Cited by 26
Explainable Artificial Intelligence Solution for Online Retail
Javaid, K., Siddiqa, A., Naqvi, S. A. Z., Ditta, A., Ahsan, M. S., Khan, M. A., Mahmood, T., & Khan, M. A. (2022) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.022984 · Cited by 21
Development of a Malicious Network Traffic Intrusion Detection System Using Deep Learning
Isife, O., Okokpujie, K., Okokpujie, I. P., Subair, R. E., Akingunsoye, A. V., & Awomoyi, M. E. (2023) · International Journal of Safety and Security Engineering · doi:10.18280/ijsse.130401 · Cited by 20
An Incremental Majority Voting Approach for Intrusion Detection System Based on Machine Learning
Ugli, A. A. A., & Shin, J. S. (2024) · IEEE Access · doi:10.1109/access.2024.3361041 · Cited by 20
“In order to tackle above mentioned threats, The field of intrusion detection has witnessed numerous studies [6], [7], [8] employing both machine learning and deep learning approaches [9] to address the challenges in network security.”
BackgroundA Novel IDS with a Dynamic Access Control Algorithm to Detect and Defend Intrusion at IoT Nodes
Alazab, M., Awajan, A. W., Alazzam, H., Wedyan, M., Alshawi, B., & Alturki, R. (2024) · Sensors · doi:10.3390/s24072188 · Cited by 22
“H. Liu et al. surveyed multiple DL models for intrusion detection [25].”
BackgroundRastogi, S., Shrotriya, A., Singh, M. K., & Vamsi, P. R. (2022) · Journal of Computing Research and Innovation · doi:10.24191/jcrinn.v7i1.274 · Cited by 19
“…the network for signs of malicious activity (Rashid, Siddique, & Ahmed, 2020; Heine, Laue, & Kleiner, 2020; Chauhan & Vamsi, 2019; Aziz & Abdulazeez, 2021; Ahmad, Shahid Khan, Wai Shiang, Abdullah, & Ahmad, 2021; Mahfouz, Venugopal, & Shiva, 2020; Liu & Lang, 2019; Dhanabal & Shantharajah, 2015).”
Qaddoori, S. L., & Ali, Q. I. (2022) · IET Information Security · doi:10.1049/ise2.12097 · Cited by 19
Deep learning techniques to detect cybersecurity attacks: a systematic mapping study
Torre, D., Mesadieu, F., & Chennamaneni, A. (2023) · Empirical Software Engineering · doi:10.1007/s10664-023-10302-1 · Cited by 27
“DL is a subset of ML algorithms that are based on artificial neural networks that can achieve superior performances (Liu and Lang 2019).”
BackgroundMethodInfluentialGrigoraș, C. C., Zichil, V., Ciubotariu, V. A., & Cosa, S. M. (2024) · Machines · doi:10.3390/machines12030180 · Cited by 19
Survey on Unified Threat Management (UTM) Systems for Home Networks
Siddiqui, A., Rimal, B. P., Reisslein, M., & Wang, Y. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3382470 · Cited by 25
Integrated Photonic Neural Networks for Equalizing Optical Communication Signals: A Review
Silva, L. C. B., Marciano, P. R. N., Pontes, M. J., Monteiro, M. E., André, P. S. D. B., & Segatto, M. E. V. (2025) · Photonics · doi:10.3390/photonics12010039 · Cited by 22
Uppal, M., Gulzar, Y., Gupta, D., Uppal, J., Kumar, M., & Saini, S. (2025) · Discover Internet of Things · doi:10.1007/s43926-025-00101-z · Cited by 21
Alzubi, Q. M., Makhadmeh, S. N., & Sanjalawe, Y. K. (2025) · Journal of Advances in Information Technology · doi:10.12720/jait.16.3.283-302 · Cited by 27
“The importance of cybersecurity research has risen because of the widespread use of networks nowadays [5].”
InfluentialDouimia, S., Bekrar, A., Cadi, A. A. E., Hillali, Y. E., & Fillon, D. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.103034 · Cited by 20
USB-IDS-1: a Public Multilayer Dataset of Labeled Network Flows for IDS Evaluation
Catillo, M., Vecchio, A. D., Ocone, L., Pecchia, A., & Villano, U. (2021) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w52860.2021.00012 · Cited by 20
“For example, with the rapid growth of deep learning frameworks, many attack detectors have spread in the literature [6], [7]; noteworthy, some of these detectors achieve very encouraging results in terms of detection rate, which is close to 100% on public datasets.”
BackgroundA Payload Based Malicious HTTP Traffic Detection Method Using Transfer Semi-Supervised Learning
Chen, T., Chen, Y., Lv, M., He, G., Zhu, T., Wang, T., & Weng, Z. (2021) · Applied Sciences · doi:10.3390/app11167188 · Cited by 21
“Most state-of-the-art payload based methods adopt learning techniques for malicious network traffic detection, including traditional machine learning techniques [8–11] and deep learning techniques [12–16].”
BackgroundVisual Digital Forest Model Based on a Remote Sensing Data and Forest Inventory Data
Вагизов, М. Р., Istomin, E., Valerie Miheev, L., Artem Potapov, P., & Yagotinceva, N. (2021) · Remote Sensing · doi:10.3390/rs13204092 · Cited by 20
A Marine Hydrographic Station Networks Intrusion Detection Method Based on LCVAE and CNN-BiLSTM
Hou, T., Xing, H., Liang, X., Su, X., & Wang, Z. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11010221 · Cited by 18
Testing the Resilience of MEC-Based IoT Applications Against Resource Exhaustion Attacks
Pietrantuono, R., Ficco, M., & Palmieri, F. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3263137 · Cited by 19
“…stage is not to build a classifier for attack detection (an attack detection algorithm needs to consider other factors besides features engineering [40]), filter methods are the best option, as they are computationally fast and independent of any downstream classifier that could be used at later…”
BackgroundIdentification of Network Traffic Intrusion Using Decision Tree
Chen, D., Song, Q., Zhang, Y., Li, L., & Yang, Z. (2023) · Journal of Sensors · doi:10.1155/2023/5997304 · Cited by 18
Zhang, Y., Fu, B., Sun, X., Yao, H., Zhang, S., Wu, Y., Kuang, H., & Deng, T. (2023) · Remote Sensing · doi:10.3390/rs15164003 · Cited by 18
“Machine learning algorithms have the advantages of strong model generalization [28] and can automate the processing of large amounts of data [29], and joint OBIA and machine learning algorithms have become one of the important methods for fine classification of wetland vegetation in recent years [30–32].”
BackgroundA Multi-Modal Deep Transfer Learning Framework for Attack Detection in Software-Defined Networks
Elubeyd, H., Yiltas-Kaplan, D., & Bahtıyar, Ş. (2023) · IEEE Access · doi:10.1109/access.2023.3324878 · Cited by 18
Clusters in chaos: A deep unsupervised learning paradigm for network anomaly detection
Perumal, S., Sujatha, P. K., Krishnaa, S., & Krishnan, M. (2024) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2024.104083 · Cited by 18
The Complex Method of Intrusion Detection Based on Anomaly Detection and Misuse Detection
Радівілова, Т., Kirichenko, L., Alghawli, A. S., Ilkov, A., Tawalbeh, M., & Zinchenko, P. (2020) · International Conference on Dependable Systems, Services and Technologies (DESSERT) · doi:10.1109/dessert50317.2020.9125051 · Cited by 18
“The authors of [18] described the IDS taxonomy and surveyed machine learning and deep learning methods in IDS for cybersecurity.”
BackgroundMethodA survey on the application of deep learning for code injection detection
Abaimov, S., & Bianchi, G. (2021) · Array · doi:10.1016/j.array.2021.100077 · Cited by 20
Multiresolution dendritic cell algorithm for network anomaly detection
Limon-Cantu, D., & Alarcon‐Aquino, V. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.749 · Cited by 18
Artificial intelligence techniques
Shafiullah, M., Abido, M. A., & Al-Mohammed, A. H. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-88429-7.00007-2 · Cited by 19
Effective intrusion detection system using concept drifting data stream and support vector machine
Rajeswari, P. V. N., Mogalla, S., Rao, T. K., Lakshmi, M. R., & Kiran, L. V. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7118 · Cited by 21
“Output: Attack or normal do { Enable SVM classifier SVM do { Equations (8) and (9) generate the margin for every feature; Based on learning, the testing data packets are examined; Classified the normal from the attack packets; } } Therefore,thenormalandtheattackareefficientlyclassifiedusingtheproposedsystem.”
MethodEmpirical Analysis of Data Streaming and Batch Learning Models for Network Intrusion Detection
Adewole, K. S., Salau-Ibrahim, T. T., Imoize, A. L., Oladipo, I. D., AbdulRaheem, M., Awotunde, J. B., Balogun, A. O., Isiaka, R. M., & Aro, T. O. (2022) · Electronics · doi:10.3390/electronics11193109 · Cited by 18
“To identify and describe ML-based and DL-based IDS, the authors of [15] suggest an IDS ontology in which data objects serve as the primary criterion for identification.”
MethodAlsharif, W. M. (2023) · Saudi Medical Journal · doi:10.15537/smj.2023.44.2.20220611 · Cited by 21
“19 20-25 The literature refers to the potential role of DL-CAD regarding enhancing diagnostic accuracy and specificity in breast screening.”
BackgroundKatlav, M., Ergen, F., Türk, K., & Turğut, P. (2024) · Materials Today Communications · doi:10.1016/j.mtcomm.2024.108141 · Cited by 18
Leveraging AI for enhanced cybersecurity: a comprehensive review
Swetha, T., Kumaran, U. S., Meena, V., & Hameed, I. A. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-06773-0 · Cited by 20
“Bo Lang et al. [78] provides a comprehensive overview of ML and DL techniques are applied to IDS.”
CND-IDS: Continual Novelty Detection for Intrusion Detection Systems
Fuhrman, S., Güngör, O., & Rosing, T. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11132541 · Cited by 17
“The literature proposes various ML models, including supervised models such as support vector machine, random forest, deep neural networks [18], and unsupervised models like isolation forest, autoencoder, and principal component analysis [14].”
A Secure IoT Framework Based on Blockchain and Machine Learning
Shahin, R., & Sabri, K. E. (2022) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/110154 · Cited by 17
“These algorithms are selected as they are well known classifiers in IDS and are efficient in term of time [25] [26].”
MethodIntrusion Traffic Detection and Classification Based on Unsupervised Learning
Zhong, Z., Xie, C., & Tang, X. (2024) · IEEE Access · doi:10.1109/access.2024.3400213 · Cited by 17
“The unsupervised learning algorithm can extract the corresponding feature information from the unlabeled data and obtain the training data more conveniently [12].”
BackgroundNetwork Threat Detection Based on Group CNN for Privacy Protection
Xu, Y., Zhang, X., Lu, C., Qiu, Z., Bi, C., Lai, Y., Qiu, J., & Zhang, H. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/3697536 · Cited by 20
“In this situation, intrusion detection [13], malicious code detection [14], malware detection [15], malicious URL detection [16], and vulnerability mining [17] based on machine learning algorithms are considered to be e ff ective network threat behavior detection measures.”
BackgroundMethodInfluentialHosseinpour, S., Pirdashti, H., Hosseinpour, D., Mousavi, H., & Mohammadpour, S. (2025) · Modeling Earth Systems and Environment · doi:10.1007/s40808-025-02456-2 · Cited by 16
“However, these high complexities also affect training and testing times, increasing runtimes (Liu and Lang 2019).”
García, P., de Curtò, J., de Zarzà, I., Cano, J., & Calafate, C. T. (2025) · Electronics · doi:10.3390/electronics14193792 · Cited by 20
A Complete Review on the Application of Statistical Methods for Evaluating Internet Traffic Usage
Cunha, V. C., Zavala, A. A. Z., Magoni, D., Inácio, P. R. M., & Freire, M. M. (2022) · IEEE Access · doi:10.1109/access.2022.3227073 · Cited by 17
“The main difference between our research and other review works [2], [3], [8], [10], [16], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], and [6] is that our proposal addresses solutions to solve traffic classification problems by using…”
BackgroundAn Optimized Hybrid Deep Intrusion Detection Model (HD-IDM) for Enhancing Network Security
Ahmad, I. A., Imran, M. A., Qayyum, A., Ramzan, M. S., & Alassafi, M. O. (2023) · Mathematics · doi:10.3390/math11214501 · Cited by 16
Alrumaih, T. N. I., & Alenazi, M. J. F. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3390691 · Cited by 16
“In this line, machine learning (ML) techniques, which can learn from unbalanced data together with proper feature engineering to detect new attack patterns, provide a better generalization to detect unknown attack sequences [10].”
BackgroundAnomaly detection in log-event sequences: A federated deep learning approach and open challenges
Himler, P., Landauer, M., Skopik, F., & Wurzenberger, M. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100554 · Cited by 26
IDRandom-Forest: Advanced Random Forest for Real-Time Intrusion Detection
Azhar, M. H., Perveen, S., Iqbal, A., & Lee, B. (2024) · IEEE Access · doi:10.1109/access.2024.3443408 · Cited by 22
“Over the last decade, deep learning-based techniques have been extensively used for intrusion detection [9], [10], [11] and other fields [12], [13].”
BackgroundAn Intrusion Detection System Model Based on Bidirectional LSTM
Alsyaibani, O. M. A., Utami, E., & Hartanto, A. D. (2021) · International Conference on Cybernetics and Intelligent System (ICORIS) · doi:10.1109/icoris52787.2021.9649612 · Cited by 16
An Optimized and Hybrid Framework for Image Processing Based Network Intrusion Detection System
Siddiqi, M. A., & Pak, W. (2022) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.029541 · Cited by 23
Pham, T., Le, T., Dang, D., Bui, H., Pham, H. N., Truong, L., Nguyen, M., Vo, T.-H., & Quan, T. (2022) · IEEE Access · doi:10.1109/access.2022.3217478 · Cited by 16
“In addition, recent surveys on various domains also show that the shallow learning models hardly scale due to the overfit [31], [32].”
BackgroundSecurity Baseline for Substation Automation Systems
Horálek, J., & Sobĕslav, V. (2023) · Sensors · doi:10.3390/s23167125 · Cited by 20
“Machine Learning and Deep Learning have high potential applicability in Methods for Intrusion Detection Systems, which is addressed in [41], and also for the IoT domain, as reported in [42,43].”
BackgroundClassification of UNSW-NB15 dataset using Exploratory Data Analysis using Ensemble Learning
Sharma, N. V., Yadav, N. S., & Sharma, S. (2021) · EAI Endorsed Transactions on Industrial Networks and Intelligent Systems · doi:10.4108/eai.13-10-2021.171319 · Cited by 18
“These evaluation parameters are calculated from the confusion matrix which is the measure of true positive, true negatives, false positive, false negatives for a classification algorithm calculated over a validation dataset [4] (Liu & Lang, 2019).”
MethodDesign of a Network Intrusion Detection System Using Complex Deep Neuronal Networks
Al-Shabi, M. (2021) · International Journal of Communication Networks and Information Security (IJCNIS) · doi:10.17762/ijcnis.v13i3.5148 · Cited by 15
A Clustering Strategy for Enhanced FL-Based Intrusion Detection in IoT Networks
Talpini, J., Sartori, F., & Savi, M. (2023) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0011627500003393 · Cited by 15
“In recent years, data-driven approaches for developing IDSs have been explored (Shone et al., 2018; Liu and Lang, 2019; Tauscher et al., 2021) considering different methods such as random forests, support vector machines, neural networks or clustering techniques.”
MethodFeature Importance-Based Backdoor Attack in NSL-KDD
Jang, J., An, Y., Kim, D., & Choi, D. (2023) · Electronics · doi:10.3390/electronics12244953 · Cited by 15
Cluster and Conquer: Malicious Traffic Classification at the Edge
Diallo, A. F., & Patras, P. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3342716 · Cited by 15
“In this context, Artificial Intelligence (AI)- and Machine Learning (ML)-based techniques such as Artificial Neural Networks, Clustering, and Ensemble Learning are increasingly appealing for building automatic network threat or anomaly detection systems [9], [10].”
MethodE-SDNN: encoder-stacked deep neural networks for DDOS attack detection
Benmohamed, E., Thaljaoui, A., Khediri, S. E., Aladhadh, S., & Alohali, M. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09622-0 · Cited by 16
Rigorous Evaluation of Machine Learning-Based Intrusion Detection Against Adversarial Attacks
Güngör, O., Li, E., Shang, Z., Guo, Y., Chen, J., Davis, J., & Rosing, T. (2024) · IEEE International Conference on Cyber Security and Resilience (CSR) · doi:10.1109/csr61664.2024.10679443 · Cited by 20
“Machine learning (ML) has become a popular IDS solution due to its strong generalizability in detecting attack variants and novel attacks [5].”
BackgroundMethodJohn, A., Isnin, I. F., Madni, S. H. H., & Faheem, M. (2024) · IET Wireless Sensor Systems · doi:10.1049/wss2.12100 · Cited by 16
Deep Learning Applications for Intrusion Detection in Network Traffic
Getman, A. I., Rybolovlev, D. A., & Nikolskaya, A. G. (2024) · Programming and Computer Software · doi:10.1134/s0361768824700221 · Cited by 16
“The paper [29] presented a literature review on the use of machine learning and neural networks in IDS from a perspective of the IDS taxonomy proposed by the authors.”
FGA-IDS: A Federated Learning and GAN-Augmented Intrusion Detection System for UAV Networks
Zeng, Q., Olatunde-Salawu, S., & Naït‐Abdesselam, F. (2024) · IEEE International Conference on Collaboration and Internet Computing (CIC) · doi:10.1109/cic62241.2024.00017 · Cited by 15
“In recent years, machine learning (ML) techniques have been increasingly employed to enhance the effectiveness of IDS, enabling more accurate and adaptive threat detection [5].”
Application of Machine Learning Algorithms to Predict Urban Expansion
Robi, R. K., & George, J. K. (2025) · Journal of Urban Planning and Development · doi:10.1061/jupddm.upeng-5466 · Cited by 15
Omer, S. Z., Hashim, F., Sali, A. B., & Ahmad, F. A. (2025) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2025.102049 · Cited by 23
Autoencoder-based Intrusion Detection System
Kamalov, F., Zgheib, R., Leung, H., Al-Gindy, A., & Moussa, S. (2021) · International Conference on Engineering and Emerging Technologies (ICEET) · doi:10.1109/iceet53442.2021.9659562 · Cited by 15
Ensemble Machine Learning Techniques for Attack Prediction in NIDS Environment
Reddy, T. S., & Sathya, R. (2022) · Iraqi Journal for Computer Science and Mathematics · doi:10.52866/ijcsm.2022.02.01.008 · Cited by 15
A Quasi-Newton Neural Network Based Efficient Intrusion Detection System for Wireless Sensor Network
Alagarsamy, G., Shanthini, J., & Karthik, S. (2022) · Computer Systems Science and Engineering · doi:10.32604/csse.2023.026688 · Cited by 15
Lifetime prediction of electronic devices based on the P-stacking machine learning model
Wang, F., Yang, Y., Huang, T., & Xu, Y. (2023) · Microelectronics Reliability · doi:10.1016/j.microrel.2023.115027 · Cited by 16
Human Skeleton Data Augmentation for Person Identification over Deep Neural Network
Kwon, B., & Lee, S. (2020) · Applied Sciences · doi:10.3390/app10144849 · Cited by 15
Decision Tree-Based Rule Derivation for Intrusion Detection in Safety-Critical Automotive Systems
Buschlinger, L., Rieke, R., Sarda, S., & Kraus, C. (2022) · 2022 30th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP) · doi:10.1109/pdp55904.2022.00046 · Cited by 14
“The ML-specific accuracies generally fall in line with those that the related works (e.g., [11], [28], [29]) have observed.”
BackgroundResultAlom, J., Ullah, M. S., Islam, M. T., Niloy, M., Islam, R., & Firdaus, S. (2025) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain66474.2025.11172169 · Cited by 14
“Intrusion detection systems (IDS) have traditionally relied on centralized data collection [3] and machine learning models trained on labeled network traffic [4].”
Razzaq, H. S., & Hussain, Z. M. (2022) · Information · doi:10.3390/info14010018 · Cited by 15
Kumar, V. (2023) · International Journal of Data Informatics and Intelligent Computing · doi:10.59461/ijdiic.v2i2.58 · Cited by 14
“Therefore, it is essential to create IDSs that can recognize unidentified assaults [3-4].”
BackgroundCollaborative Federated Learning-Based Model for Alert Correlation and Attack Scenario Recognition
Alkhpor, H. K., & Alserhani, F. (2023) · Electronics · doi:10.3390/electronics12214509 · Cited by 15
Uncertainty-Quantified, Robust Deep Learning for Network Intrusion Detection
Wong, J. A., Berenbeim, A., Bierbrauer, D., & Bastian, N. D. (2023) · Winter Simulation Conference · doi:10.1109/wsc60868.2023.10407559 · Cited by 20
“A few benchmark datasets used for network intrusion detection are KDD Cup’99, Kyoto 2006+, NSL-KDD, and CSE-CICIDS-2018 (Ahmad et al. 2021; Shone et al. 2018; Kim et al. 2017; Liu and Lang 2019; Almseidin et al. 2017; Almiani et al. 2020).”
BackgroundMethodFederated Learning for Privacy-Preserving Intrusion Detection in IoT Networks
Azeez, S. D., Ilyas, M., & Bakko, I. M. (2024) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora61326.2024.10550685 · Cited by 16
“[ 18] Collected by Liu and Lang are works that discuss applications of machine learning and deep learning for intrusion detection systems, which introduce a new technology and could be advantageous in getting more accurate detection.”
BackgroundIntelligent SDN to enhance security in IoT networks
Ibrahim, S., Youssef, A., Shoman, M. A. I., & Taha, S. (2024) · Egyptian Informatics Journal · doi:10.1016/j.eij.2024.100564 · Cited by 18
Rabbi, F., Hossain, N. U. I., & Das, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126718 · Cited by 15
Improving Intrusion Detection Systems by Using Deep Learning Methods on Time Series Data
Mohammed, A. A. A. (2025) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.9417 · Cited by 14
“In this regard, a relevant review showed that existing approaches are divided into two main classes, traditional methods and modern deep learning frameworks, with respective strengths and weaknesses [1, 7, 8].”
Iwanowski, M., Olszewski, D., Graniszewski, W., Krupski, J., & Pelc, F. (2025) · Applied Sciences · doi:10.3390/app15158466 · Cited by 17
Adaptive Network Intrusion Detection Using Reinforcement Learning with Proximal Policy Optimization
Suresh, A., & Jose, A. C. (2025) · ACM Transactions on Privacy and Security · doi:10.1145/3764586 · Cited by 19
“Traditional machine learning ( ML ) approaches have emerged as valuable tools in the fight against cyber threats, forming the backbone of many modern anomaly detection and intrusion detection systems [37].”
A Survey on Network Intrusion Detection using Convolutional Neural Network
Kaissar, A., Nassif, A. B., & Injadat, M. (2022) · ITM Web of Conferences · doi:10.1051/itmconf/20224301003 · Cited by 14
“[5] illustrates all machine learning algorithms where it’s split into shallow and deep learning.”
BackgroundInfluentialBekri, M. E. (2023) · Journal of Internet Services and Information Security · doi:10.58346/jisis.2023.i2.010 · Cited by 14
Ghamdi, M. A. A. (2023) · IEEE Access · doi:10.1109/access.2023.3307018 · Cited by 14
“IDSs [15], [16] can alternatively be categorized as abuse detection or anomaly detection based on their detection methods, contingent upon whether or not the intrusion patterns are known before the strategy process.”
BackgroundA survey on Deep Learning based Intrusion Detection Systems on Internet of Things
Slevi, S. T., & Visalakshi, P. (2021) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac52330.2021.9641050 · Cited by 15
A Survey on Learning-Based Intrusion Detection Systems for IoT Networks
Abdelhamid, S., Aref, M. M., Hegazy, I., & Roushdy, M. I. (2021) · International Conference on Intelligent Computing and Information Systems (ICICIS) · doi:10.1109/icicis52592.2021.9694226 · Cited by 15
FlowWise: Stateful Fast-Slow Model Serving for Streaming Traffic Intelligence
Liu, S., Shaowang, T., Wan, G., Chae, J., Marques, J. A., Krishnan, S., & Feamster, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.03694 · Cited by 14
Kamil, W. F., & Mohammed, I. J. (2023) · Iraqi Journal of Science · doi:10.24996/ijs.2023.64.9.43 · Cited by 13
Deshpande, N. M., Gite, S., Pradhan, B., Alamri, A. M., & Lee, C.-W. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.030704 · Cited by 16
Christodoulou, P., & Limniotis, K. (2024) · Network · doi:10.3390/network4010005 · Cited by 15
“…as a type of artificial intelligence (AI) algorithms, are widely used in various fields, such as digital image processing [1], data analytics [2], autonomous systems [3], text and speech recognition [4], face recognition [5], robotics [6], traffic prediction [7], intrusion detection [8], etc.”
Quantum Machine Learning in Intrusion Detection Systems: A Systematic Mapping Study
Faker, O., & Çağıltay, N. E. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-7886-1_9 · Cited by 15
Yin, L., Chen, W., Luo, X., & Hongyu, Y. (2024) · Mathematics · doi:10.3390/math12091315 · Cited by 17
“Due to its powerful representation learning ability, deep learning can discover informative features from complex representations and is particularly suitable for feature extraction in the field of botnet detection [26].”
Backgroundde Souza, C. A., Westphall, C. B., Valencio, J. D. G., Machado, R. B., & Bezerra, W. D. R. (2024) · Ad Hoc Networks · doi:10.1016/j.adhoc.2024.103541 · Cited by 13
Saadouni, R., Gherbi, C., Aliouat, Z., Harbi, Y., Khacha, A., & Mabed, H. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101422 · Cited by 13
Zouhri, H., & Idri, A. (2024) · World Conference on Complex Systems · doi:10.1109/wccs62745.2024.10765501 · Cited by 13
“To solve this problem, current research is focusing on Artificial Intelligence (AI) and ML approaches to create generalizable IDSs due to their capacity to analyze large volumes of data and accurately identify anomalies [2] .”
Clustering-Based Intrusion Detection System Meets Multicritics Generative Adversarial Networks
Wang, H., Kandah, F. I., Mendis, T., & Medury, L. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3533918 · Cited by 16
“Moreover, IDSs relying on a single type of ML or deep learning model often face challenges in maintaining high accuracy across multiple types of attacks, where multiple network attacks may occur simultaneously [15].”
CGFL: A Robust Federated Learning Approach for Intrusion Detection Systems Based on Data Generation
Feng, S., Gao, L., & Shi, L. (2025) · Applied Sciences · doi:10.3390/app15052416 · Cited by 13
ConvGRU: A Lightweight Intrusion Detection System for Vehicle Networks Based on Shallow CNN and GRU
Wang, S., Cheng, J., Wang, Y., Li, S., Kang, L., & Dai, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3563908 · Cited by 17
“As a result, there is ongoing exploration into the utilization of machine learning techniques for network intrusion detection systems to address the limitations of current solutions [21].”
Huang, J., Hu, D., Ding, Z., & Wu, X. (2022) · IEEE Wireless Communications · doi:10.1109/mwc.004.2100362 · Cited by 14
Explainable AI for Intrusion Detection Systems
Ramyavarshini, P., Sriram, G. K., Rajasekaran, U., & Malini, A. (2022) · International Conference on Contemporary Computing and Informatics (IC3I) · doi:10.1109/ic3i56241.2022.10073356 · Cited by 15
“This paper tells that interpretable nature of models would become an essential research area in the upcoming years[7].”
BackgroundNuiaa, R. R., Alomari, E. S., Mortatha, M. B., Alyasseri, Z. A. A., Mohammed, M. A., Dhanaraj, R. K., Manickam, S., Kadry, S., Anbar, M., & Karuppayah, S. (2023) · Wireless Networks · doi:10.1007/s11276-023-03606-z · Cited by 24
“In practice, it is unlikely that all input features are independent [21, 28].”
Exploiting the Outcome of Outlier Detection for Novel Attack Pattern Recognition on Streaming Data
Heigl, M., Weigelt, E., Urmann, A., Fiala, D., & Schramm, M. (2021) · Electronics · doi:10.3390/electronics10172160 · Cited by 13
Lakshminarayana, S. K., & Basarkod, P. I. (2023) · Wireless Personal Communications · doi:10.1007/s11277-023-10722-8 · Cited by 12
“Among various existing machine learning (ML) techniques, k-nearest neighbor (KNN) classifier is widely adopted in the most of machine learning applications due to its better detection rate [11].”
Background
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.