A Study on Network Anomaly Detection Using Fast Persistent Contrastive Divergence

被引:0
作者
Jeong, Jaeyeong [1 ,2 ]
Park, Seongmin [3 ]
Lim, Joonhyung [3 ]
Kang, Jiwon [1 ,4 ]
Shin, Dongil [1 ]
Shin, Dongkyoo [1 ,2 ,4 ]
机构
[1] Sejong Univ, Dept Comp Sci & Engn, Seoul 05006, South Korea
[2] Sejong Univ, Convergence Major Intelligent Drone, Seoul 05006, South Korea
[3] Korea Internet & Secur Agcy, Infrastruct Secur Technol Team, Naju 58324, South Korea
[4] Sejong Univ, Cyber Warfare Res Inst, Seoul 05006, South Korea
来源
SYMMETRY-BASEL | 2024年 / 16卷 / 09期
关键词
network intrusion detection system; anomaly detection; fast persistent contrastive divergence; deep belief network; INTRUSION DETECTION;
D O I
10.3390/sym16091220
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
As network technology evolves, cyberattacks are not only increasing in frequency but also becoming more sophisticated. To proactively detect and prevent these cyberattacks, researchers are developing intrusion detection systems (IDSs) leveraging machine learning and deep learning techniques. However, a significant challenge with these advanced models is the increased training time as model complexity grows, and the symmetry between performance and training time must be taken into account. To address this issue, this study proposes a fast-persistent-contrastive-divergence-based deep belief network (FPCD-DBN) that offers both high accuracy and rapid training times. This model combines the efficiency of contrastive divergence with the powerful feature extraction capabilities of deep belief networks. While traditional deep belief networks use a contrastive divergence (CD) algorithm, the FPCD algorithm improves the performance of the model by passing the results of each detection layer to the next layer. In addition, the mix of parameter updates using fast weights and continuous chains makes the model fast and accurate. The performance of the proposed FPCD-DBN model was evaluated on several benchmark datasets, including NSL-KDD, UNSW-NB15, and CIC-IDS-2017. As a result, the proposed method proved to be a viable solution as the model performed well with an accuracy of 89.4% and an F1 score of 89.7%. By achieving superior performance across multiple datasets, the approach shows great potential for enhancing network security and providing a robust defense against evolving cyber threats.
引用
收藏
页数:14
相关论文
共 33 条
[1]   Analysis of KDD Dataset Attributes - Class wise For Intrusion Detection [J].
Aggarwal, Preeti ;
Sharma, Sudhir Kumar .
3RD INTERNATIONAL CONFERENCE ON RECENT TRENDS IN COMPUTING 2015 (ICRTC-2015), 2015, 57 :842-851
[2]   An evaluation of the performance of Restricted Boltzmann Machines as a model for anomaly network intrusion detection [J].
Aldwairi, Tamer ;
Perera, Dilina ;
Novotny, Mark A. .
COMPUTER NETWORKS, 2018, 144 :111-119
[3]  
[Anonymous], 2009, Scholarpedia
[4]  
Aygun R. Can, 2017, 2017 IEEE 4th International Conference on Cyber-Security and Cloud Computing (CSCloud), P193, DOI 10.1109/CSCloud.2017.39
[5]  
Bace R. G., 2001, NIST special publication on intrusion detection systems
[6]  
Barbir A., RFC 4593: Generic Threats to Routing Protocols
[7]  
Berglund M., 2013, arXiv, DOI [10.48550/arXiv.1312.6002, DOI 10.48550/ARXIV.1312.6002]
[8]  
Carreira-Perpinan M. A., 2005, P 10 INT WORKSH ART, VR5, P33
[9]  
Cisco Annual Internet Report-Cisco Annual Internet Report, 2018, White Paper
[10]  
Fischer A, 2012, Proceedings, P14, DOI [10.1007/978-3-642-33275-3{\\_}2, DOI 10.1007/978-3-642-33275-3]