Research Article
BibTex RIS Cite

Machine Learning based Network Intrusion Detection with Hybrid Frequent Item Set Mining

Year 2024, EARLY VIEW, 1 - 1
https://doi.org/10.2339/politeknik.1386467

Abstract

With the development and expansion of computer networks day by day and the diversity of software developed, the damage that possible attacks can cause is increasing beyond the predictions. Intrusion Detection Systems (STS/IDS) are one of the effective defense tools against these potential attacks that are constantly increasing and diversifying. The ultimate goal is to train these systems with various artificial intelligence methods, to detect subsequent attacks in real time and to take the necessary precautions. In this study, classical feature selection methods and Frequent Item Set Mining were used in feature selection in a hybrid model, and it was aimed to classify network traffic data for normal and attack by using many machine learning methods, including Logistic Regression, with the final features obtained. The method uses a data set originally containing 85 features to make a decision while making this classification. These attributes are extracted using CICFlowMeter from a PCAP file where network traffic is recorded. The results show that the proposed method in the study classifies more than 225000 records in the data set with a success rate of 97.68%.

References

  • [1] Awadh K. and Akbas A., “Intrusion detection model based on TF.IDF and C4.5 algorithms”, Politeknik Dergisi, 24:(4), 1691–1698, (2021).
  • [2] Akbas A. and Buyrukoglu S., “Deep belief network based wireless sensor network connectivity analysis,” Balkan Journal of Electrical and Computer Engineering, 11: 262–266, (2023).
  • [3] Uyan O. G., Akbas A., and Gungor V. C., “Machine learning approaches for underwater sensor network parameter prediction,” Ad Hoc Networks, 144:103-139, (2023).
  • [4] Altunay H. C. and Albayrak Z., “Network intrusion detection approach based on convolutional neural network,” Avrupa Bilim ve Teknoloji Dergisi, 26: 22–29, (2021).
  • [5] Karaman M. S., Turan M., and Aydin M. A., “Yapay Sinir Ağı Kullanılarak Anomali Tabanlı Saldırı Tespit Modeli Uygulaması,” Avrupa Bilim ve Teknoloji Dergisi, Ejosat Ek Ozel Sayi (HORA): 10–17, (2020).
  • [6] Bakhshi T. and Ghita B., “Anomaly detection in encrypted internet traffic using hybrid deep learning,” Security and Communication Networks, 1–16, (2021).
  • [7] Wei S., Zhang Z., Li S., and Jiang P., “Calibrating network traffic with one-dimensional convolutional neural network with autoencoder and independent recurrent neural network for mobile malware detection,” Security and Communication Networks, (2021):1–10, (2021).
  • [8] Arslan R. S., “Fasttrafficanalyzer: An efficient method for intrusion detection systems to analyze network traffic,” Dicle Universitesi Muhendislik Fakultesi Muhendislik Dergisi, 12:(4) 565–572, (2021).
  • [9] Pehlivanoglu M. K., Remzi A., and Odabas D. E., “Iki seviyeli hibrit makine ogrenmesi yontemi ile saldiri tespiti,” Gazi Muhendislik Bilimleri Dergisi, 5:(3), 258–272, (2019).
  • [10] Ozekes S. and Karakoc E. N., “Makine ogrenmesi yontemleriyle anormal ag trafiginin tespit edilmesi,” Duzce universitesi Bilim ve Teknoloji Dergisi, 7:(1), 566–576, (2019).
  • [11] Tokyurek E., “Birliktelik kural cikarim algoritmalari kullanilarak market sepet analizi,” Master’s thesis, Bilecik Seyh Edebali Universitesi, Fen Bilimleri Enstitusu, (2019).
  • [12] Hidayanto B. C., Muhammad R. F., Kusumawardani R. P., and Syafaat A., “Network intrusion detection systems analysis using frequent item set mining algorithm fp-max and apriori,” Procedia Computer Science, 124:751–758, (2017).
  • [13] Moustafa N. and Slay J., “A hybrid feature selection for network intrusion detection systems: Central points,” arXiv preprint arXiv:1707.05505, (2017).
  • [14] Aung K. M. M. and Oo N. N., “Association rule pattern mining approaches network anomaly detection,” Ph.D. dissertation, Meral Portal, (2015).
  • [15] Nalavade K. and Meshram B., “Mining association rules to evade network intrusion in network audit data,” International Journal of Advanced Computer Research, 4:(2), 560, (2014).
  • [16] Sokhangoee Z. F. and Rezapour A., “A novel approach for spam detection based on association rule mining and genetic algorithm,” Computers & Electrical Engineering, 97: 107655, (2022).
  • [17] Cekmez U., Erdem Z., Yavuz A. G., Sahingoz O. K., and Buldu A., “Network anomaly detection with deep learning,” in 2018 26th Signal Processing and Communications Applications Conference (SIU). IEEE, 1–4, (2018).
  • [18] IDS 2017 Datasets- canadian institute for cybersecurity, https://www.unb.ca/cic/datasets/ids-2017.html, (Accessed on 06/30/2023).
  • [19] Budak H., “Ozellik secim yontemleri ve yeni bir yaklasim,” Suleyman Demirel Universitesi Fen Bilimleri Enstitusu Dergisi, 22: 21–31, (2018).
  • [20] Erkantarci B. and Bakal G., “An empirical study of sentiment analysis utilizing machine learning and deep learning algorithms,” Journal of Computational Social Science, 1–17, (2023).
  • [21] Bakal G., Talari P., Kakani E. V., and Kavuluru R., “Exploiting semantic patterns over biomedical knowledge graphs for predicting treatment and causative relations,” Journal of biomedical informatics, 82:189–199, (2018).
  • [22] Bakal G. and Kavuluru R., “Predicting treatment relations with semantic patterns over biomedical knowledge graphs,” in International Conference on Mining Intelligence and Knowledge Exploration. Springer, 586–596, (2015).
  • [23] Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., and Duchesnay E., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, 12: 2825–2830, (2011).

Hibrit Sık Kullanılan Öğe Kümeleme ile Makine Öğrenmesi Tabanlı Ağ Sızma Tespiti

Year 2024, EARLY VIEW, 1 - 1
https://doi.org/10.2339/politeknik.1386467

Abstract

Bilgisayar ağlarının her geçen gün gelişmesi ve genişlemesi ve geliştirilen yazılımların çeşitliliği ile muhtemel saldırıların neden olabileceği zararlar tahminlerin ötesinde artmaktadır. Sızma Tespit Sistemleri (STS/IDS), sürekli artan ve çeşitlenen bu potansiyel saldırılara karşı etkili savunma araçlarından biridir. Asıl amaç, bu sistemleri çeşitli yapay zeka metotlarıyla eğiterek, sonraki saldırıları gerçek zamanlı olarak tespit etmek ve gerekli önlemleri alabilmektir. Bu çalışmada, hibrit bir modelde özellik seçiminde klasik özellik seçimi yöntemleri ve Sık Kullanılan Öğe Kümeleme kullanılmış ve elde edilen son özelliklerle, Lojistik Regresyon da dahil olmak üzere birçok makine öğrenmesi yöntemi kullanılarak ağ trafiği verilerinin normal ve saldırı için sınıflandırılması amaçlanmıştır. Yöntem, bu sınıflandırmayı yaparken özgün olarak 85 özelliği içeren bir veri setini karar vermede kullanmaktadır. Bu özellikler, ağ trafiğinin kaydedildiği bir PCAP dosyasından CICFlowMeter kullanılarak çıkarılmaktadır. Sonuçlar, çalışmada önerilen yöntemin veri setindeki 225000'den fazla kaydı %97,68 başarı oranı ile sınıflandırdığını göstermektedir.

References

  • [1] Awadh K. and Akbas A., “Intrusion detection model based on TF.IDF and C4.5 algorithms”, Politeknik Dergisi, 24:(4), 1691–1698, (2021).
  • [2] Akbas A. and Buyrukoglu S., “Deep belief network based wireless sensor network connectivity analysis,” Balkan Journal of Electrical and Computer Engineering, 11: 262–266, (2023).
  • [3] Uyan O. G., Akbas A., and Gungor V. C., “Machine learning approaches for underwater sensor network parameter prediction,” Ad Hoc Networks, 144:103-139, (2023).
  • [4] Altunay H. C. and Albayrak Z., “Network intrusion detection approach based on convolutional neural network,” Avrupa Bilim ve Teknoloji Dergisi, 26: 22–29, (2021).
  • [5] Karaman M. S., Turan M., and Aydin M. A., “Yapay Sinir Ağı Kullanılarak Anomali Tabanlı Saldırı Tespit Modeli Uygulaması,” Avrupa Bilim ve Teknoloji Dergisi, Ejosat Ek Ozel Sayi (HORA): 10–17, (2020).
  • [6] Bakhshi T. and Ghita B., “Anomaly detection in encrypted internet traffic using hybrid deep learning,” Security and Communication Networks, 1–16, (2021).
  • [7] Wei S., Zhang Z., Li S., and Jiang P., “Calibrating network traffic with one-dimensional convolutional neural network with autoencoder and independent recurrent neural network for mobile malware detection,” Security and Communication Networks, (2021):1–10, (2021).
  • [8] Arslan R. S., “Fasttrafficanalyzer: An efficient method for intrusion detection systems to analyze network traffic,” Dicle Universitesi Muhendislik Fakultesi Muhendislik Dergisi, 12:(4) 565–572, (2021).
  • [9] Pehlivanoglu M. K., Remzi A., and Odabas D. E., “Iki seviyeli hibrit makine ogrenmesi yontemi ile saldiri tespiti,” Gazi Muhendislik Bilimleri Dergisi, 5:(3), 258–272, (2019).
  • [10] Ozekes S. and Karakoc E. N., “Makine ogrenmesi yontemleriyle anormal ag trafiginin tespit edilmesi,” Duzce universitesi Bilim ve Teknoloji Dergisi, 7:(1), 566–576, (2019).
  • [11] Tokyurek E., “Birliktelik kural cikarim algoritmalari kullanilarak market sepet analizi,” Master’s thesis, Bilecik Seyh Edebali Universitesi, Fen Bilimleri Enstitusu, (2019).
  • [12] Hidayanto B. C., Muhammad R. F., Kusumawardani R. P., and Syafaat A., “Network intrusion detection systems analysis using frequent item set mining algorithm fp-max and apriori,” Procedia Computer Science, 124:751–758, (2017).
  • [13] Moustafa N. and Slay J., “A hybrid feature selection for network intrusion detection systems: Central points,” arXiv preprint arXiv:1707.05505, (2017).
  • [14] Aung K. M. M. and Oo N. N., “Association rule pattern mining approaches network anomaly detection,” Ph.D. dissertation, Meral Portal, (2015).
  • [15] Nalavade K. and Meshram B., “Mining association rules to evade network intrusion in network audit data,” International Journal of Advanced Computer Research, 4:(2), 560, (2014).
  • [16] Sokhangoee Z. F. and Rezapour A., “A novel approach for spam detection based on association rule mining and genetic algorithm,” Computers & Electrical Engineering, 97: 107655, (2022).
  • [17] Cekmez U., Erdem Z., Yavuz A. G., Sahingoz O. K., and Buldu A., “Network anomaly detection with deep learning,” in 2018 26th Signal Processing and Communications Applications Conference (SIU). IEEE, 1–4, (2018).
  • [18] IDS 2017 Datasets- canadian institute for cybersecurity, https://www.unb.ca/cic/datasets/ids-2017.html, (Accessed on 06/30/2023).
  • [19] Budak H., “Ozellik secim yontemleri ve yeni bir yaklasim,” Suleyman Demirel Universitesi Fen Bilimleri Enstitusu Dergisi, 22: 21–31, (2018).
  • [20] Erkantarci B. and Bakal G., “An empirical study of sentiment analysis utilizing machine learning and deep learning algorithms,” Journal of Computational Social Science, 1–17, (2023).
  • [21] Bakal G., Talari P., Kakani E. V., and Kavuluru R., “Exploiting semantic patterns over biomedical knowledge graphs for predicting treatment and causative relations,” Journal of biomedical informatics, 82:189–199, (2018).
  • [22] Bakal G. and Kavuluru R., “Predicting treatment relations with semantic patterns over biomedical knowledge graphs,” in International Conference on Mining Intelligence and Knowledge Exploration. Springer, 586–596, (2015).
  • [23] Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., and Duchesnay E., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, 12: 2825–2830, (2011).
There are 23 citations in total.

Details

Primary Language English
Subjects Machine Learning (Other)
Journal Section Research Article
Authors

Murat Firat 0009-0009-0113-9868

Mehmet Gökhan Bakal 0000-0003-2897-3894

Ayhan Akbaş 0000-0002-6425-104X

Early Pub Date January 18, 2024
Publication Date
Submission Date November 6, 2023
Acceptance Date December 25, 2023
Published in Issue Year 2024 EARLY VIEW

Cite

APA Firat, M., Bakal, M. G., & Akbaş, A. (2024). Machine Learning based Network Intrusion Detection with Hybrid Frequent Item Set Mining. Politeknik Dergisi1-1. https://doi.org/10.2339/politeknik.1386467
AMA Firat M, Bakal MG, Akbaş A. Machine Learning based Network Intrusion Detection with Hybrid Frequent Item Set Mining. Politeknik Dergisi. Published online January 1, 2024:1-1. doi:10.2339/politeknik.1386467
Chicago Firat, Murat, Mehmet Gökhan Bakal, and Ayhan Akbaş. “Machine Learning Based Network Intrusion Detection With Hybrid Frequent Item Set Mining”. Politeknik Dergisi, January (January 2024), 1-1. https://doi.org/10.2339/politeknik.1386467.
EndNote Firat M, Bakal MG, Akbaş A (January 1, 2024) Machine Learning based Network Intrusion Detection with Hybrid Frequent Item Set Mining. Politeknik Dergisi 1–1.
IEEE M. Firat, M. G. Bakal, and A. Akbaş, “Machine Learning based Network Intrusion Detection with Hybrid Frequent Item Set Mining”, Politeknik Dergisi, pp. 1–1, January 2024, doi: 10.2339/politeknik.1386467.
ISNAD Firat, Murat et al. “Machine Learning Based Network Intrusion Detection With Hybrid Frequent Item Set Mining”. Politeknik Dergisi. January 2024. 1-1. https://doi.org/10.2339/politeknik.1386467.
JAMA Firat M, Bakal MG, Akbaş A. Machine Learning based Network Intrusion Detection with Hybrid Frequent Item Set Mining. Politeknik Dergisi. 2024;:1–1.
MLA Firat, Murat et al. “Machine Learning Based Network Intrusion Detection With Hybrid Frequent Item Set Mining”. Politeknik Dergisi, 2024, pp. 1-1, doi:10.2339/politeknik.1386467.
Vancouver Firat M, Bakal MG, Akbaş A. Machine Learning based Network Intrusion Detection with Hybrid Frequent Item Set Mining. Politeknik Dergisi. 2024:1-.