Research on Network Intrusion Detection Technology Based on Machine Learning

Wu, Fei; Li, Ting; Wu, Zhen; Wu, Shulin; Xiao, Chuanqi

doi:10.1007/s10776-021-00520-z

Cited by 18 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GAN-Cross model uses DNN as a hidden layer to capture highly nonlinear relationships between data. Take the randomly generated hidden space noise z and the corresponding class label y as the input of the generator, passing through the cross-layers The cross-operation is shown in formula (1).…”

Section: R E T R a C T E D A R T I C L Ementioning

confidence: 99%

“…Currently, network security attacks occur frequently. At a time when cyber security attacks pose a serious threat and their destructive attack power is becoming increasingly serious, how to gain early and timely insight into and grasp the development trend of cyber security, understand the harmful techniques of various new cyber security attacks, and make targeted and effective proactive responses to them has gradually become a common research focus in different fields [1,2]. Network intrusion detection system (NIDS) can actively detect attacks through network traffic analysis, and it plays a crucial role in network security [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

RETRACTED ARTICLE: Fusion of transformer and ML-CNN-BiLSTM for network intrusion detection

Xiang

2023

J Wireless Com Network

View full text Add to dashboard Cite

Network intrusion detection system (NIDS) can effectively sense network attacks, which is of great significance for maintaining the security of cyberspace. To meet the requirements of efficient and accurate network status monitoring, a NIDS model using Transformer-based fusion deep learning architecture is proposed. Firstly, GAN-Cross is used to expand minority class sample data, thereby alleviating the issues of imbalanced minority class about the original dataset. Then, the Transformer module is used to adjust the ML-CNN-BiLSTM model to enhance the feature encoding ability of the intrusion model. Finally, the data enhancement model and feature enhancement model are integrated into the NIDS model, the detection model is optimized, the features of network state data are extracted at a deeper level, and the generalization ability of the detection model is enhanced. Some simulation experiments using UNSW-NB15 datasets show that the proposed fusion architecture can achieve efficient analysis of complex network traffic datasets, with an accuracy of 0.903, effectively improving the detection accuracy of NIDS and its ability to detect unknown attacks. The proposed model has good application value in ensuring the stable operation of network systems.

show abstract

Section: R E T R a C T E D A R T I C L Ementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Fusion of transformer and ML-CNN-BiLSTM for network intrusion detection

Xiang

2023

J Wireless Com Network

View full text Add to dashboard Cite

show abstract

“…Drawing on the advantages of deep learning, traditional machine learning algorithms are combined with feature selection and are widely applied in the field of network intrusion detection, such as random forest, support vector machine, K-nearest neighbor, decision tree, etc. [19,20], all of which have achieved good results. Commonly used datasets related to intrusion detection include KDD Cup 99, DARPA 1998, ADFA-LD, CIC-IDS2017, UNSW-NB15, etc.…”

Section: Literature Reviewmentioning

confidence: 95%

Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy

et al. 2022

View full text Add to dashboard Cite

This paper proposes a novel network anomaly detection framework based on data balance and feature selection. Different from the previous binary classification of network intrusion, the network anomaly detection strategy proposed in this paper solves the problem of multiple classification of network intrusion. Regarding the common data imbalance of a network intrusion detection set, a resampling strategy generated by random sampling and Borderline SMOTE data is developed for data balance. According to the features of the intrusion detection dataset, feature selection is carried out based on information gain rate. Experiments are carried out on three basic machine learning algorithms (K-nearest neighbor algorithm (KNN), decision tree (DT), random forest (RF)), and the optimal feature selection scheme is obtained.

show abstract

“…The effectiveness of the random forest is better in terms of precision, accuracy, and F-measure. F. Wu et al [42] Analyzed the four classes of attack detection using the dataset KDDCUP99 by the application improved random forest-support vector machine learning model. The average accuracy of this model is 97.04%, which is less than compared to the new techniques.…”

Section: Ac = (5)mentioning

confidence: 99%

Detection and Analysis of Flooding Attacks in Wireless Sensor Networks

Gebremariam

Panda

Indu

2022

Preprint

View full text Add to dashboard Cite

Wireless sensor networks are distributed networks and randomly deployed in harsh environments. The scattered nature of the sensor nodes in an unattended environment makes them vulnerable to various types of attacks. Multiple attacks like flooding attacks degrade the network performance and lifetime by sending various requests to malicious nodes. This paper proposes the detection and analysis of flooding attacks in mesh wireless sensor networks using the Blue tooth communication package MATLAB 2020a toolbox. The flooding attack disabled the relay nodes during the routing path between sources and destination nodes for each simulation scenario. The simulations are conducted by the number of sensors variation for the random generator. After simulating the meshed nodes, the statistical results are the message delivery chance, average hope count, and critical relays. The opportunity of message delivery having a route between sources and destinations is 88.64%. The effectiveness of the proposed system for detection and analysis of flooding attacks is evaluated by random forest machine earing techniques with an average detection rate and accuracy of 99.83%, which is greater than by 3.8%.

show abstract

Research on Network Intrusion Detection Technology Based on Machine Learning

Cited by 18 publications

References 18 publications

RETRACTED ARTICLE: Fusion of transformer and ML-CNN-BiLSTM for network intrusion detection

RETRACTED ARTICLE: Fusion of transformer and ML-CNN-BiLSTM for network intrusion detection

Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy

Detection and Analysis of Flooding Attacks in Wireless Sensor Networks

Contact Info

Product

Resources

About