The DOI matches its Crossref record; 87 of the 89 references it cites were found in a registry or an index.
Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey
Open accessAbstract
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].”
BackgroundCNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2014.131 · Cited by 4,451 · cited 1×
“CNNs are designed to mimic the human visual system (HVS); consequently, CNNs have made great achievements in the computer vision field [23–25].”
Background(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051 · cited 1×
“Many famous autoencoder variants exist, such as denoising autoencoders [14,15] and sparse autoencoders [16].”
BackgroundMoustafa, N., & Slay, J. (2015) · 2015 Military Communications and Information Systems Conference (MilCIS) · doi:10.1109/milcis.2015.7348942 · Cited by 4,033 · cited 4×
“The UNSW-NB15 is representative of new IDS datasets, and has been used in some recent studies.”
MethodInfluentialDenning, D. E. (1987) · IEEE Transactions on Software Engineering · doi:10.1109/tse.1987.232894 · Cited by 3,427 · cited 1×
“An IDS is a computer-security application that aims to detect a wide range of security violations, ranging from attempted break-ins by outsiders to system penetrations and abuses by insiders [6].”
BackgroundA Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection
Buczak, A. L., & Guven, E. (2016) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2015.2494502 · Cited by 3,332 · cited 1×
“Several previous surveys [3–5] have classified research efforts by their applied machine learning algorithms.”
BackgroundFace recognition: a convolutional neural-network approach
Lawrence, S., Giles, C. L., Tsoi, A. C., & Back, A. D. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.554195 · Cited by 3,092 · cited 1×
“CNNs are designed to mimic the human visual system (HVS); consequently, CNNs have made great achievements in the computer vision field [23–25].”
BackgroundA Practical Guide to Training Restricted Boltzmann Machines
Hinton, G. E. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_32 · Cited by 2,852 · cited 1×
“RBMs are unsupervised learning models trained by the contrastive divergence algorithm [17], and they are usually applied for feature extraction or denoising.”
MethodTowards End-To-End Speech Recognition with Recurrent Neural Networks
Graves, A., & Jaitly, N. (2014) · Cited by 1,861
A Deep Learning Approach to Network Intrusion Detection
Shone, N., Ngoc, T. N., Phai, V. D., & Shi, Q. (2018) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2017.2772792 · Cited by 1,819 · cited 1×
“Parallel computing [66,67] approaches using GPUs [48,68,69] are common solutions.”
MethodN-BaIoT—Network-Based Detection of IoT Botnet Attacks Using Deep Autoencoders
Meidan, Y., Bohadana, M., Mathov, Y., Mirsky, Y., Shabtai, A., Breitenbacher, D., & Elovici, Y. (2018) · IEEE Pervasive Computing · doi:10.1109/mprv.2018.03367731 · Cited by 1,483
Machine Learning and Deep Learning Methods for Cybersecurity
Xin, Y., Kong, L., Liu, Z., Chen, Y., Li, Y., Zhu, H., Gao, M., Hou, H., & Wang, C. (2018) · IEEE Access · doi:10.1109/access.2018.2836950 · Cited by 1,228
Interpretable Explanations of Black Boxes by Meaningful Perturbation
Fong, R. C., & Vedaldi, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.371 · Cited by 1,097 · cited 1×
“Deep learning models are black boxes [32–35]; the results are almost uninterpretable, which is a critical point in deep learning.”
BackgroundHe, Y., Mendis, G. J., & Wei, J. (2017) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2017.2703842 · Cited by 834 · cited 1×
“For specific application scenarios, such as cloud computing [82,83], IoT [84–86], and smart grids [87,88], domain knowledge can be used to provide the environmental characteristics that are helpful in data collection and data preprocessing.”
BackgroundSparse Feature Learning for Deep Belief Networks
Ranzato, M., Boureau, Y.-L., & LeCun, Y. (2007) · neural information processing systems · Cited by 744
Random Forest Modeling for Network Intrusion Detection System
Farnaaz, N., & Jabbar, M. A. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.06.047 · Cited by 684
Machine Learning DDoS Detection for Consumer Internet of Things Devices
Doshi, R., Apthorpe, N., & Feamster, N. (2018) · 2018 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00013 · Cited by 680 · cited 1×
“For specific application scenarios, such as cloud computing [82,83], IoT [84–86], and smart grids [87,88], domain knowledge can be used to provide the environmental characteristics that are helpful in data collection and data preprocessing.”
BackgroundWang, W., Sheng, Y., Wang, J., Zeng, X., Ye, X., Huang, Y., & Zhu, M. (2018) · IEEE Access · doi:10.1109/access.2017.2780250 · Cited by 655 · cited 1×
“Wang et al. [58] proposed a hierarchical deep learning detection method in which a session contains not only packet contents but also the packet time sequence.”
MethodCNN Features off-the-shelf: an Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · arXiv · doi:10.48550/arxiv.1403.6382 · Cited by 607 · cited 1×
“CNNs are designed to mimic the human visual system (HVS); consequently, CNNs have made great achievements in the computer vision field [23–25].”
BackgroundSurvey on Anomaly Detection using Data Mining Techniques
Agrawal, S., & Agrawal, J. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.08.220 · Cited by 595 · cited 1×
“Several previous surveys [3–5] have classified research efforts by their applied machine learning algorithms.”
BackgroundUnderstanding Neural Networks through Representation Erasure
Li, J., Monroe, W., & Jurafsky, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.08220 · Cited by 412
DeepDefense: Identifying DDoS Attack via Deep Learning
Yuan, X., Li, C., & Li, X. (2017) · 2017 IEEE International Conference on Smart Computing (SMARTCOMP) · doi:10.1109/smartcomp.2017.7946998 · Cited by 390 · cited 2×
“[56] Session CNN and LSTM ISCX 2012 Radford et al.”
MethodHeberlein, L. T., Dias, G. V., Levitt, K. N., Mukherjee, B., Wood, J., & Wolber, D. (1990) · Proceedings. 1990 IEEE Computer Society Symposium on Research in Security and Privacy · doi:10.1109/risp.1990.63859 · Cited by 381
Sparse Autoencoder-Based Feature Transfer Learning for Speech Emotion Recognition
Deng, J., Zhang, Z., Marchi, E., & Schuller, B. (2013) · 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction · doi:10.1109/acii.2013.90 · Cited by 366 · cited 1×
“Many famous autoencoder variants exist, such as denoising autoencoders [14,15] and sparse autoencoders [16].”
BackgroundToward an Online Anomaly Intrusion Detection System Based on Deep Learning
Alrawashdeh, K., & Purdy, C. (2016) · 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA) · doi:10.1109/icmla.2016.0040 · Cited by 287
LEMNA: Explaining Deep Learning based Security Applications
Guo, W., Mu, D., Xu, J., Su, P., Wang, G., & Xing, X. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243792 · Cited by 287 · cited 1×
“These models report only the detection results and have no interpretable basis [93].”
BackgroundClustering Approach Based on Mini Batch Kmeans for Intrusion Detection System Over Big Data
Peng, K., Leung, V. C. M., & Huang, Q. (2018) · IEEE Access · doi:10.1109/access.2018.2810267 · Cited by 268 · cited 1×
“To improve detection efficiency, Peng et al. [13] proposed an improved K-means detection method with mini batch.”
MethodA Novel Hierarchical Intrusion Detection System Based on Decision Tree and Rules-Based Models
Ahmim, A., Maglaras, L., Ferrag, M. A., Derdour, M., & Janicke, H. (2019) · 2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS) · doi:10.1109/dcoss.2019.00059 · Cited by 266 · cited 2×
“[54] Session Decision tree CICIDS 2017 Alseiari et al.”
MethodZeng, Y., Gu, H., Wei, W., & Guo, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2908225 · Cited by 260 · cited 1×
“Zeng et al. [44] proposed a payload detection method with multiple deep learning models.”
MethodCollective Anomaly Detection Based on Long Short-Term Memory Recurrent Neural Networks
Bontemps, L., Cao, V. L., McDermott, J., & Le-Khac, N.-A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-48057-2_9 · Cited by 245 · cited 1×
“For specific types of attacks, such as DOS [74–79], botnet [80], and phishing web [81], proper feature must be extracted according to the attack characteristics that can be abstracted using domain knowledge.”
BackgroundMa, T., Wang, F., Cheng, J., Yu, Y., & Chen, X. (2016) · Sensors · doi:10.3390/s16101701 · Cited by 230
Shah, S. A. R., & Issac, B. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2017.10.016 · Cited by 224 · cited 1×
“Combining machine learning methods with rule-based systems, such as Snort [70–73], can result in IDSs with low false alarm rates and low missed alarm rates.”
MethodMethod of intrusion detection using deep neural network
Kim, J., Shin, N., Jo, S. Y., & Kim, S. H. (2017) · 2017 IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp.2017.7881684 · Cited by 223 · cited 1×
“Parallel computing [66,67] approaches using GPUs [48,68,69] are common solutions.”
MethodAccelerated deep neural networks for enhanced Intrusion Detection System
Potluri, S., & Diedrich, C. (2016) · 2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2016.7733515 · Cited by 212 · cited 1×
“Parallel computing [66,67] approaches using GPUs [48,68,69] are common solutions.”
MethodCNN and RNN based payload classification methods for attack detection
Liu, H., Lang, B., Liu, M., & Yan, H. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.08.036 · Cited by 209 · cited 1×
“As a type of unstructured data, payloads can be processed directly by deep learning models [42].”
BackgroundSelf-citationDetecting Distributed Denial of Service Attacks Using Data Mining Techniques
Alkasassbeh, M., Al-Naymat, G., B.A, A., & Almseidin, M. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.070159 · Cited by 192
Leveraging LSTM Networks for Attack Detection in Fog-to-Things Communications
Diro, A., & Chilamkurti, N. (2018) · IEEE Communications Magazine · doi:10.1109/mcom.2018.1701270 · Cited by 190 · cited 1×
“For specific application scenarios, such as cloud computing [82,83], IoT [84–86], and smart grids [87,88], domain knowledge can be used to provide the environmental characteristics that are helpful in data collection and data preprocessing.”
BackgroundA Deep Learning Based DDoS Detection System in Software-Defined Networking (SDN)
Niyaz, Q., Sun, W., & Javaid, A. Y. (2017) · ICST Transactions on Security and Safety · doi:10.4108/eai.28-12-2017.153515 · Cited by 185
Two-tier network anomaly detection model: a machine learning approach
Pajouh, H. H., Dastghaibyfard, G., & Hashemi, S. (2017) · Journal of Intelligent Information Systems · doi:10.1007/s10844-015-0388-x · Cited by 180 · cited 4×
“The SMOTE algorithm oversamples the minority classes and divides the majority classes into many subclasses so that every class is balanced.”
MethodInfluentialMachine Learning Based DDoS Attack Detection from Source Side in Cloud
He, Z., Zhang, T., & Lee, R. B. (2017) · 2017 IEEE 4th International Conference on Cyber Security and Cloud Computing (CSCloud) · doi:10.1109/cscloud.2017.58 · Cited by 178 · cited 1×
“• For specific application scenarios, such as cloud computing [82,83], IoT [84–86], and smart grids [87,88], domain knowledge can be used to provide the environmental characteristics that are helpful in data collection and data preprocessing.”
BackgroundMin, E., Long, J., Liu, Q., Cui, J., & Chen, W. (2018) · Security and Communication Networks · doi:10.1155/2018/4943509 · Cited by 175 · cited 1×
“Min et al. [43] utilized a text-based CNN to detect attacks from payloads.”
BackgroundNetwork Intrusion Detection through Stacking Dilated Convolutional Autoencoders
Yu, Y., Long, J., & Cai, Z. (2017) · Security and Communication Networks · doi:10.1155/2017/4184196 · Cited by 169 · cited 1×
“Yu et al. [45] utilized a convolutional autoencoder to extract payload features and conducted experiments on the CTU-UNB dataset.”
MethodRavale, U., Marathe, N., & Padiya, P. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.03.174 · Cited by 168
Bringing a GAN to a Knife-Fight: Adapting Malware Communication to Avoid Detection
Rigaki, M., & Garcia, S. (2018) · 2018 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00019 · Cited by 167 · cited 1×
“Rigaki et al. [46] used a GAN to improve the malware detection effect.”
MethodYang, Y., Zheng, K., Wu, C., Niu, X., & Yang, Y. (2019) · Applied Sciences · doi:10.3390/app9020238 · Cited by 167 · cited 1×
“In attack detection, DBNs are used for both feature extraction and classification [20–22].”
MethodIntrusion Detection System Based on Decision Tree over Big Data in Fog Environment
Peng, K., Leung, V. C. M., Zheng, L., Wang, S., Huang, C., & Lin, T. (2018) · Wireless Communications and Mobile Computing · doi:10.1155/2018/4680867 · Cited by 158 · cited 1×
“For specific application scenarios, such as cloud computing [82,83], IoT [84–86], and smart grids [87,88], domain knowledge can be used to provide the environmental characteristics that are helpful in data collection and data preprocessing.”
BackgroundForoutan, S. A., & Salmasi, F. R. (2017) · IET Cyber-Physical Systems Theory & Applications · doi:10.1049/iet-cps.2017.0013 · Cited by 153 · cited 1×
“For specific application scenarios, such as cloud computing [82,83], IoT [84–86], and smart grids [87,88], domain knowledge can be used to provide the environmental characteristics that are helpful in data collection and data preprocessing.”
BackgroundIntrusion Detection Using Deep Belief Network and Probabilistic Neural Network
Zhao, G., Zhang, C., & Zheng, L. (2017) · 22017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC) · doi:10.1109/cse-euc.2017.119 · Cited by 149 · cited 1×
“In attack detection, DBNs are used for both feature extraction and classification [20–22].”
MethodSVM-DT-based adaptive and collaborative intrusion detection
Teng, S., Wu, N., Zhu, H., Teng, L., & Zhang, W. (2017) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2017.7510730 · Cited by 137 · cited 1×
“Teng et al. [52] proposed an SVM detection method based on protocol grouping using the data of the KDD99 dataset, which involves various protocols.”
MethodGoeschel, K. (2016) · IEEE SoutheastCon · doi:10.1109/secon.2016.7506774 · Cited by 136 · cited 2×
“[47] Flow SVM, decision tree, and Naïve Bayes KDD99 Kuttranont et al.”
MethodApplied Machine Learning predictive analytics to SQL Injection Attack detection and prevention
Uwagbole, S. O., Buchanan, W. J., & Fan, L. (2017) · IFIP/IEEE International Symposium on Integrated Network Management (IM) · doi:10.23919/inm.2017.7987433 · Cited by 133 · cited 2×
“[64] proposed an SQL-injection detection method for the Internet of Things (IoT).”
MethodKuang, F., Zhang, S., Jin, Z., & Xu, W. (2014) · Soft Computing · doi:10.1007/s00500-014-1332-7 · Cited by 128
An anomaly detection method to detect web attacks using Stacked Auto-Encoder
Vartouni, A. M., Kashi, S. S., & Teshnehlab, M. (2018) · Iranian Joint Congress on Fuzzy and Intelligent Systems · doi:10.1109/cfis.2018.8336654 · Cited by 127 · cited 2×
“[65] Log Isolate forest CSIC 2010 dataset”
MethodAbdelhamid, N., Thabtah, F., & Abdel-Jaber, H. (2017) · IEEE International Conference on Intelligence and Security Informatics (ISI) · doi:10.1109/isi.2017.8004877 · Cited by 118 · cited 1×
“• For specific types of attacks, such as DOS [74–79], botnet [80], and phishing web [81], proper feature must be extracted according to the attack characteristics that can be abstracted using domain knowledge.”
BackgroundConvolutional Neural Networks for Multi-class Intrusion Detection System
Potluri, S., Ahmed, S., & Diedrich, C. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05918-7_20 · Cited by 96
Meng, W., Li, W., & Kwok, L. F. (2015) · Security and Communication Networks · doi:10.1002/sec.1307 · Cited by 91
Use of machine learning in big data analytics for insider threat detection
Mayhew, M. J., Atighetchi, M., Adler, A., & Greenstadt, R. (2015) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom.2015.7357562 · Cited by 82 · cited 2×
“[40] proposed an SVM- and K-means-based packet detection method.”
MethodFrequency based DDoS attack detection approach using naive Bayes classification
Fouladi, R. F., Kayataş, C. E., & Anarım, E. (2016) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2016.7760838 · Cited by 82 · cited 1×
“For specific types of attacks, such as DOS [74–79], botnet [80], and phishing web [81], proper feature must be extracted according to the attack characteristics that can be abstracted using domain knowledge.”
BackgroundDetection of Application Layer DDoS attack by feature learning using Stacked AutoEncoder
Yadav, S., & Subramanian, S. (2016) · International Conference on Computational Techniques in Information and Communication Technologies · doi:10.1109/icctict.2016.7514608 · Cited by 80
Intrusion detection system using hybrid binary PSO and K-nearest neighborhood algorithm
Syarif, A. R., & Gata, W. (2017) · International Conference on Information & Communication Technology and System (ICTS) · doi:10.1109/icts.2017.8265667 · Cited by 78
Network Intrusion Detection Based on Stacked Sparse Autoencoder and Binary Tree Ensemble Method
Zhang, B., Yu, Y., & Li, J. (2018) · IEEE International Conference on Communications workshops · doi:10.1109/iccw.2018.8403759 · Cited by 71 · cited 2×
“[50] extracted features with a sparse autoencoder and detected attacks with an XGBoost model.”
MethodNguyen, S.-N., Nguyen, V.-Q., Choi, J., & Kim, K. (2018) · International Conference on Machine Learning and Soft Computing (ICMLSC) · doi:10.1145/3184066.3184089 · Cited by 63
Deep learning to detect botnet via network flow summaries
Pektaş, A., & Acarman, T. (2018) · Neural Computing and Applications · doi:10.1007/s00521-018-3595-x · Cited by 60
Identifying malicious botnet traffic using logistic regression
Bapat, R., Mandya, A., Liu, X., Abraham, B., Brown, D. E., Kang, H., & Veeraraghavan, M. (2018) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds.2018.8374749 · Cited by 59 · cited 1×
“For specific types of attacks, such as DOS [74–79], botnet [80], and phishing web [81], proper feature must be extracted according to the attack characteristics that can be abstracted using domain knowledge.”
BackgroundCluster Based Ensemble Classification for Intrusion Detection System
Jabbar, M. A., Aluvalu, R., & Reddy, S. S. S. (2017) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3055635.3056595 · Cited by 56
Deep learning for prioritizing and responding to intrusion detection alerts
McElwee, S., Heaton, J., Fraley, J. B., & Cannady, J. (2017) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom.2017.8170757 · Cited by 56 · cited 1×
“[60] proposed an alert filtering method based on a DNN.”
MethodKhamphakdee, N., Benjamas, N., & Saiyod, S. (2015) · Journal of ICT Research and Applications · doi:10.5614/itbj.ict.res.appl.2015.8.3.4 · Cited by 45
An Approach for Host-Based Intrusion Detection System Design Using Convolutional Neural Network
Tran, N. N., Sarker, R. A., & Hu, J. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-319-90775-8_10 · Cited by 43 · cited 2×
“[61] proposed a CNN method to analyze system calls.”
MethodIntrusion detection in enterprise systems by combining and clustering diverse monitor data
Bohara, A., Thakore, U., & Sanders, W. H. (2016) · Symposium and Bootcamp on Science of Security · doi:10.1145/2898375.2898400 · Cited by 42 · cited 2×
“[63] Log K-means and DBSCAN VAST 2011 Mini Challenge 2”
MethodA Decision Tree Classifier for Intrusion Detection Priority Tagging
Ammar, A. (2015) · Journal of Computer and Communications · doi:10.4236/jcc.2015.34006 · Cited by 41 · cited 1×
“Combining machine learning methods with rule-based systems, such as Snort [70–73], can result in IDSs with low false alarm rates and low missed alarm rates.”
MethodAlseiari, F. A. A., & Aung, Z. (2015) · International Conference on Smart Grid and Clean Energy Technologies · doi:10.1109/icsgce.2015.7454287 · Cited by 40
Mahmood, H. A. (2018) · Al-Mustansiriyah Journal of Sciences · doi:10.23851/mjs.v28i2.508 · Cited by 37 · cited 1×
“Naïve Bayes Robust to noise; Able to learn incrementally Do not perform well on attribute-related data Imported latent variables to relax the independent assumption [11]”
BackgroundShah, R. A., Qian, Y., Kumar, D., Ali, M., & Alvi, M. B. (2017) · Future Internet · doi:10.3390/fi9040081 · Cited by 34 · cited 1×
“LR Simple, can be trained rapidly; Automatically scale features Do not perform well on nonlinear data; Apt to overfitting Imported regularization to avoid overfitting [12]”
BackgroundFalse positive elimination in intrusion detection based on clustering
Hu, L., Li, T., Xie, N., & Hu, J. (2015) · International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) · doi:10.1109/fskd.2015.7381996 · Cited by 28 · cited 1×
“[41] proposed a fuzzy C-means based packet detection method.”
MethodParallel KNN and Neighborhood Classification Implementations on GPU for Network Intrusion Detection
Kuttranont, P., Boonprakob, K., Phaudphut, C., Permpol, S., Aimtongkhamand, P., Kokaew, U., Waikham, B., & So–In, C. (2017) · Journal of Telecommunication Electronic and Computer Engineering (JTEC) · Cited by 24
Effective Intrusion Detection System using Data Mining Technique
Patel, J., & Panchal, K. (2015) · Journal of Emerging Technologies and Innovative Research · Cited by 16
An innovative two-stage fuzzy kNN-DST classifier for unknown intrusion detection
Jing, X., Bi, Y., & Deng, H. (2016) · The International Arab Journal of Information Technology · Cited by 6
Deep Learning for Unsupervised Insider Threat Detection in Structured Cybersecurity Data Streams
Tuor, A., Kaplan, S., Hutchinson, B., Nichols, N., & Robinson, S. (2017) · arXiv · doi:10.48550/arxiv.1710.00811
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
Ahmad, Z., Shahid Khan, A., Wai Shiang, C., Abdullah, J., & Ahmad, F. (2021) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4150 · Cited by 1,288
Cyber risk and cybersecurity: a systematic review of data availability
Cremer, F., Sheehan, B., Fortmann, M., Kia, A. N., Mullins, M., Murphy, F., & Materne, S. (2022) · The Geneva Papers on Risk and Insurance - Issues and Practice · doi:10.1057/s41288-022-00266-6 · Cited by 355
“Liu and Lang (2019) proposed a taxonomy of intrusion detection systems that uses data objects as the main dimension to classify and summarise machine learning and deep learning-based intrusion detection literature.”
BackgroundAğbulut, Ü., Gürel, A. E., & Biçen, Y. (2021) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2020.110114 · Cited by 424
Deep Learning-Based Intrusion Detection Systems: A Systematic Review
Lansky, J., Ali, S., Mohammadi, M., Majeed, M. K., Karim, S. H. T., Rashidi, S., Hosseinzadeh, M., & Rahmani, A. M. (2021) · IEEE Access · doi:10.1109/access.2021.3097247 · Cited by 333
Zhang, H., Huang, L., Wu, C. Q., & Li, Z. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107315 · Cited by 344
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.