Multi-class SVM based network intrusion detection with attribute selection using infinite feature selection technique

Kaushik, Ruchi; Singh, Vijander; Kumar, R. Ganesh

doi:10.1080/09720529.2021.2009189

Cited by 8 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As listed in Table 3, we compare the proposed model with classic machine learning classifiers and deep learning models on testing set on multi-class scenario. The experimental results show that the key indicators of RF 18 , SVM 19 and KNN 20 are significantly lower than the deep learning models. But their detection time is faster than deep learning models, since they have only a few parameters for the purpose of classification.…”

Section: Performance Comparison Experimentsmentioning

confidence: 98%

“…During comparison experiments, we compare the proposed MSCBL-ADN model with RF 18 , SVM 19 and KNN 20 shallow classifiers on testing set. We also compare it with CNN-based models (CNN-BMECapSA-RF 25 , LRDADF 27 ), LSTM-based models (VLSTM 30 ), and CNN-LSTM-based models (AsyncFL-bLAM 16 , NIDS-CNN-LSTM 33 ) during training and testing phase.…”

Section: Performance Comparison Experimentsmentioning

confidence: 99%

“…Thus, researchers turned to LDDoS data enhancement and novel model design. At early stage, Random Forest (RF) 18 , SVM 19 , K-Near Neighbor (KNN) 20 and their enhanced shallow models with welldesigned feature engineer were adopted for LDDoS attack detection. Tang et al 21 proposed performance and features framework for LDDoS attacks based on SVM, KNN and so on.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A novel multi-scale CNN and Bi-LSTM arbitration dense network model for low-rate DDoS attack detection

Yin,

Fang,

Liu

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Low-rate distributed denial of service attacks, as known as LDDoS attacks, pose the notorious security risks in cloud computing network. They overload the cloud servers and degrade network service quality with the stealthy strategy. Furthermore, this kind of small ratio and pulse-like abnormal traffic leads to a serious data scale problem. As a result, the existing models for detecting minority and adversary LDDoS attacks are insufficient in both detection accuracy and time consumption. This paper proposes a novel multi-scale Convolutional Neural Networks (CNN) and bidirectional Long-short Term Memory (bi-LSTM) arbitration dense network model (called MSCBL-ADN) for learning and detecting LDDoS attack behaviors under the condition of limited dataset and time consumption. The MSCBL-ADN incorporates CNN for preliminary spatial feature extraction and embedding-based bi-LSTM for time relationship extraction. And then, it employs arbitration network to re-weigh feature importance for higher accuracy. At last, it uses 2-block dense connection network to perform final classification. The experimental results conducted on popular ISCX-2016-SlowDos dataset have demonstrated that the proposed MSCBL-ADN model has a significant improvement with high detection accuracy and superior time performance over the state-of-the-art models.

show abstract

Section: Performance Comparison Experimentsmentioning

confidence: 98%

Section: Performance Comparison Experimentsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A novel multi-scale CNN and Bi-LSTM arbitration dense network model for low-rate DDoS attack detection

Yin,

Fang,

Liu

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This algorithm was chosen because of its high scalability for large data sets [18] with a large number of features as in this case and because it has proven its excellent performance for IDS [35]. The computing complexity of IFS is O(n 3 × T) [36], where T is the number of samples, and n is the number of initial features.…”

Section: Infinite Feature Selection Algorithmmentioning

confidence: 99%

Mitigation of Adversarial Attacks in 5G Networks with a Robust Intrusion Detection System Based on Extremely Randomized Trees and Infinite Feature Selection

Baldini

2024

Electronics

View full text Add to dashboard Cite

Intrusion Detection Systems (IDSs) are an important tool to mitigate cybersecurity threats in the ICT infrastructures. Preferable properties of the IDSs are the optimization of the attack detection accuracy and the minimization of the computing resources and time. A signification portion of IDSs presented in the research literature is based on Machine Learning (ML) and Deep Learning (DL) elements, but they may be prone to adversarial attacks, which may undermine the overall performance of the IDS algorithm. This paper proposes a novel IDS focused on the detection of cybersecurity attacks in 5G networks, which addresses in a simple but effective way two specific adversarial attacks: (1) tampering of the labeled set used to train the ML algorithm, (2) modification of the features in the training data set. The approach is based on the combination of two algorithms, which have been introduced recently in the research literature. The first algorithm is the Extremely Randomized Tree (ERT) algorithm, which enhances the capability of Decision Tree (DT) and Random Forest (RF) algorithms to perform classification in data sets, which are unbalanced and of large size as IDS data sets usually are (legitimate traffic messages are more numerous than attack related messages). The second algorithm is the recently introduced Infinite Feature Selection algorithm, which is used to optimize the choice of the hyper-parameter defined in the approach and improve the overall computing efficiency. The result of the application of the proposed approach on a recently published 5G IDS data set proves its robustness against adversarial attacks with different degrees of severity calculated as the percentage of the tampered data set samples.

show abstract

“…The most attractive merit of Inf-FS lies that it assesses the importance of a given feature while taking all the possible subsets of features into consideration. Consequently, the Inf-FS algorithm has been applied to a wide variety of field for feature selection, and some good results have been achieved (Kaushik et al, 2021; Shao et al, 2018; Zhu et al, 2019). In this paper, the Inf-FS approach is employed to select the most informative fault features which are fed into the DCFS model for the intelligent fault diagnosis of rolling bearings.…”

Section: Introductionmentioning

confidence: 99%

Rolling bearing fault diagnosis under variable working conditions using deep convolutional fuzzy system

Zhu

Zhou

Chen

et al. 2023

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

This paper addresses the application of a deep convolutional fuzzy system (DCFS) for the fault diagnosis of rolling element bearings. The limitations of the conventional deep convolutional neural network (CNN) are the huge computational load of training the tones of parameters and the lack of interpretability for the corresponding parameters. In this paper, a DCFS-based bearing fault diagnosis method under variable working conditions is proposed. The DCFS on a high dimensional input space is a multilayer connection of many low dimensional fuzzy systems, which can overcome the computational and interpretability problems of the traditional CNN. Moreover, to improve the identification efficiency and diagnosis accuracy, the infinite feature selection (Inf-FS) algorithm is employed to select the most informative fault features. The proposed approach is experimentally demonstrated to be able to identify the different fault types and fault severities of rolling bearings under variable running states.

show abstract

Multi-class SVM based network intrusion detection with attribute selection using infinite feature selection technique

Cited by 8 publications

References 17 publications

A novel multi-scale CNN and Bi-LSTM arbitration dense network model for low-rate DDoS attack detection

A novel multi-scale CNN and Bi-LSTM arbitration dense network model for low-rate DDoS attack detection

Mitigation of Adversarial Attacks in 5G Networks with a Robust Intrusion Detection System Based on Extremely Randomized Trees and Infinite Feature Selection

Rolling bearing fault diagnosis under variable working conditions using deep convolutional fuzzy system

Contact Info

Product

Resources

About