Effective Cyber Attack Detection Based on Augmented Genetic Algorithm with Naive Bayes
Yıl 2023,
, 30 - 35, 30.12.2023
Hayriye Tanyıldız
,
Canan Batur Şahin
,
Özlem Batur Dinler
Öz
This study can be considered a vital development in the field of cyber security. Today, the ever-changing and evolving structure of cyber threats constantly challenges defense mechanisms and requires the development of innovative solutions. In this context, the application of the Naive Bayes approach enriched with genetic algorithm offers a significant contribution to existing methodologies in this field. In particular, the use of genetic algorithm in cyber-attack detection optimizes classification processes by determining the most appropriate features from data sets and thus provides a more effective detection mechanism. The integration of the Naive Bayes classifier makes it possible to detect cyber-attacks precisely and quickly based on these selected features. Empirical studies and evaluations have shown that this approach provides superior sensitivity rates and lower false positive rates than traditional techniques, demonstrating its potential to overcome the limitations of existing methods in the field of cybersecurity. These findings can be considered an important step in making cybersecurity strategies more efficient and adaptable, especially considering the constantly evolving and unpredictable nature of cyber threats. The results of this study highlight the importance of developing innovative and effective solutions in the field of cybersecurity and provide a basis for further research in this field.
Kaynakça
- Ferriyan, A. H. Thamrin, K. Takeda, and J. Murai, "Feature selection using genetic algorithm to improve classification in network intrusion detection system," 2017 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), Surabaya, Indonesia, 2017, pp. 46-49,
- Saurabh, M., Neelam Sharma, "Intrusion Detection using Naive Bayes Classifier with Feature Reduction," Procedia Technology,Volume 4,2012,Pages 119-128, ISSN 2212- 0173,
- Alimi, O., Ouahada, K., Abu Mahfouz, A.M., Rimer, S. & Alimi, K. 2022. Supervised learning-based intrusion detection for SCADA systems. http://hdl.handle.net/10204/12516
- Li, Z., Duan, M., Xiao, B., & Yang, S. (2023). A Novel Anomaly Detection Method for Digital Twin Data Using Deconvolution Operation With Attention Mechanism. IEEE Transactions on Industrial Informatics, 19, 7278-7286
- Cai Z, Du H, Wang H, Zhang J, Si Y, Li P. One Dimensional Convolutional Wasserstein Generative Adversarial Network-Based Intrusion Detection Method for Industrial Control Systems. Electronics. 2023; 12(22):4653.
- Şahin, C.B., Dinler, Ö.B. & Abualigah, L. Prediction of software vulnerability based deep symbiotic genetic algorithms: Phenotyping of dominant-features. Appl Intell 51, 8271–8287 (2021).
- Li, D., Chen, D., Jin, B., Shi, L., Goh, J., Ng, SK. (2019). MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series. ICANN 2019. Lecture Notes in Computer Science(), vol 11730. Springer, Cham.
- Audibert, J., Michiardi, P., Guyard, F., Marti, and Maria A. (Zuluaga. 2020). USAD: Unsupervised Anomaly Detection on Multivariate Time Series. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD '20). Association for Computing Machinery, New York, NY, USA, 3395–3404.
- Lyu, Y, Yaokai Feng, and Kouichi Sakurai. 2023. "A Survey on Feature Selection Techniques Based on Filtering Methods for Cyber Attack Detection." Information 14, no. 3 (2023): 191.
- https://itrust.sutd.edu.sg/itrustlabs_datasets/dataset_info/ (Accessed 3 December 2023)
- Gül, E. & Kalyoncu, M. (2021). Ağır Vasıta Hava Kompresörü Arıza Durumlarının Naive Bayes Sınıflandırıcısı ile Tahmini. Avrupa Bilim ve Teknoloji Dergisi, (31), 796-800.
- Ron, K. (2011), Scaling Up the Accuracy of Naive Bayes Classifiers: a DecisionTree Hybrid. Accessed: 24.04.2010, Association For The Advancement Of Artificial Intelligence Website.
- Nabiyev, V. V., 2016, Yapay Zeka, 5. Baskı, Seçkin Yayınları, Ankara, ISBN: 978-975-02-3727-0.
- Ebren Kara, Ş. & Şamlı, R. (2021). Genetik Algoritma İle Öznitelik Seçimi Yapılarak Yazılım Projelerinin Maliyet Tahmini. Avrupa Bilim ve Teknoloji Dergisi, (27), 985-994.
- Zahid, H., Muhammad Nadeem Yousaf, Muhammad Waqas, Muhammad Sulaiman, Ghulam Abbas, Masroor Hussain, Iftekhar Ahmad, Muhammad Hanif, "An effective genetic algorithm-based feature selection method for intrusion detection systems," Computers & Security, Volume 110, 2021, 102448, ISSN 0167-4048,
Yıl 2023,
, 30 - 35, 30.12.2023
Hayriye Tanyıldız
,
Canan Batur Şahin
,
Özlem Batur Dinler
Kaynakça
- Ferriyan, A. H. Thamrin, K. Takeda, and J. Murai, "Feature selection using genetic algorithm to improve classification in network intrusion detection system," 2017 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), Surabaya, Indonesia, 2017, pp. 46-49,
- Saurabh, M., Neelam Sharma, "Intrusion Detection using Naive Bayes Classifier with Feature Reduction," Procedia Technology,Volume 4,2012,Pages 119-128, ISSN 2212- 0173,
- Alimi, O., Ouahada, K., Abu Mahfouz, A.M., Rimer, S. & Alimi, K. 2022. Supervised learning-based intrusion detection for SCADA systems. http://hdl.handle.net/10204/12516
- Li, Z., Duan, M., Xiao, B., & Yang, S. (2023). A Novel Anomaly Detection Method for Digital Twin Data Using Deconvolution Operation With Attention Mechanism. IEEE Transactions on Industrial Informatics, 19, 7278-7286
- Cai Z, Du H, Wang H, Zhang J, Si Y, Li P. One Dimensional Convolutional Wasserstein Generative Adversarial Network-Based Intrusion Detection Method for Industrial Control Systems. Electronics. 2023; 12(22):4653.
- Şahin, C.B., Dinler, Ö.B. & Abualigah, L. Prediction of software vulnerability based deep symbiotic genetic algorithms: Phenotyping of dominant-features. Appl Intell 51, 8271–8287 (2021).
- Li, D., Chen, D., Jin, B., Shi, L., Goh, J., Ng, SK. (2019). MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series. ICANN 2019. Lecture Notes in Computer Science(), vol 11730. Springer, Cham.
- Audibert, J., Michiardi, P., Guyard, F., Marti, and Maria A. (Zuluaga. 2020). USAD: Unsupervised Anomaly Detection on Multivariate Time Series. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD '20). Association for Computing Machinery, New York, NY, USA, 3395–3404.
- Lyu, Y, Yaokai Feng, and Kouichi Sakurai. 2023. "A Survey on Feature Selection Techniques Based on Filtering Methods for Cyber Attack Detection." Information 14, no. 3 (2023): 191.
- https://itrust.sutd.edu.sg/itrustlabs_datasets/dataset_info/ (Accessed 3 December 2023)
- Gül, E. & Kalyoncu, M. (2021). Ağır Vasıta Hava Kompresörü Arıza Durumlarının Naive Bayes Sınıflandırıcısı ile Tahmini. Avrupa Bilim ve Teknoloji Dergisi, (31), 796-800.
- Ron, K. (2011), Scaling Up the Accuracy of Naive Bayes Classifiers: a DecisionTree Hybrid. Accessed: 24.04.2010, Association For The Advancement Of Artificial Intelligence Website.
- Nabiyev, V. V., 2016, Yapay Zeka, 5. Baskı, Seçkin Yayınları, Ankara, ISBN: 978-975-02-3727-0.
- Ebren Kara, Ş. & Şamlı, R. (2021). Genetik Algoritma İle Öznitelik Seçimi Yapılarak Yazılım Projelerinin Maliyet Tahmini. Avrupa Bilim ve Teknoloji Dergisi, (27), 985-994.
- Zahid, H., Muhammad Nadeem Yousaf, Muhammad Waqas, Muhammad Sulaiman, Ghulam Abbas, Masroor Hussain, Iftekhar Ahmad, Muhammad Hanif, "An effective genetic algorithm-based feature selection method for intrusion detection systems," Computers & Security, Volume 110, 2021, 102448, ISSN 0167-4048,