ENHANCING CYBERSECURITY WITH AI: A MACHINE LEARNING APPROACH TO THREAT DETECTION.

Rejina P V

doi:10.29121/shodhkosh.v2.i1.2021.5017

Authors

Rejina P V Assistant Professor ,Co-Operative Arts and Science College,Madai,Payangadi,Kannur,Kerala

DOI:

https://doi.org/10.29121/shodhkosh.v2.i1.2021.5017

Keywords:

Intrusion Detection Systems (Ids), Anomaly Detection, Cyber Threat Mitigation, Ai-Driven Security, Network Security, Intelligent Systems

Abstract [English]

With Dynamic domain cyber threats involved complexity has increased, causing challenges for traditional protection systems. An Overviewing this paper, we proposed an investigation into the impact of AI (especially ML) in bolstering cybersecurity systems with modern threat detection. The research emphasises on the design and implementation of machine learning algorithms that can detect anomalies, predict possible attacks and learn and adapt to new patterns of threat in real time. Then, a comparative analysis of supervised, unsupervised, and reinforcement learning models is provided while their applicability to requests detection is discussed. In this way, they train and evaluate the models on both real-world datasets and simulated environments. As this analysis proves, detection accuracy, response time, and zero-day attacks capability are all considerably improved compared to traditional rule-based systems after running this data on our machine learning algorithm. Future research regarding the effectiveness and implementation of AI in cybersecurity practices may also help to further develop these new frameworks or evolve how current practices are conducted in terms of machine learning, pattern recognition, and more.

References

Bhardwaj, M. D., Alshehri, K., Kaushik, H. J., Alyamani, M., & Kumar, M. (2018). Secure framework against cyber-attacks on cyber-physical robotic systems. Journal of Electronic Imaging, 31(6), 061802. https://doi.org/10.1117/1.JEI.31.6.061802 DOI: https://doi.org/10.1117/1.JEI.31.6.061802

Chithaluru, P., Fadi, A. T., Kumar, M., & Stephan, T. (2018). Computational intelligence inspired adaptive opportunistic clustering approach for industrial IoT networks. IEEE Internet of Things Journal. https://doi.org/10.1109/JIOT.2017.3231605

Barrett, M. (2018). Technical report. National Institute of Standards and Technology.

Wiafe, I., Koranteng, F. N., Obeng, E. N., Assyne, N., Wiafe, A., & Gulliver, S. R. (2015). Artificial intelligence for cybersecurity: A systematic mapping of literature. IEEE Access, 8, 146598–146612. https://doi.org/10.1109/ACCESS.2015.3015497 DOI: https://doi.org/10.1109/ACCESS.2020.3013145

Zhang, Z., Ning, H., Shi, F., Farha, F., Xu, Y., Xu, J., Zhang, F., & Choo, K. K. R. (2017). Artificial intelligence in cyber security: Research advances, challenges, and opportunities. Artificial Intelligence Review, 55, 1029–1053. https://doi.org/10.1007/s10462-021-10050-7 DOI: https://doi.org/10.1007/s10462-021-09976-0

Martínez Torres, J., Iglesias Comesaña, C., & García-Nieto, P. J. (2014). Machine learning techniques applied to cybersecurity. International Journal of Machine Learning and Cybernetics, 10(10), 2823–2836. https://doi.org/10.1007/s13042-018-00791-1 DOI: https://doi.org/10.1007/s13042-018-00906-1

Truong, T. C., Zelinka, I., Plucar, J., Čandík, M., & Šulc, V. (2015). Artificial intelligence and cybersecurity: Past, present, and future. In Artificial Intelligence and Evolutionary Computations in Engineering Systems (pp. 351–363). https://doi.org/10.1007/978-981-15-3380-8_32 DOI: https://doi.org/10.1007/978-981-15-0199-9_30

Samoili, S., Cobo, M. L., Gomez, E., De Prato, G., Martinez-Plumed, F., Delipetrev, B., & AI Watch. (2015). AI Watch: European Commission Joint Research Centre Technical Report. Joint Research Centre, Seville.

High-Level Expert Group on Artificial Intelligence (HLEG AI). (2014). A definition of AI: Main capabilities and disciplines. European Commission. https://ec.europa.eu/newsroom/dae/document.cfm?doc_id=56341

Zhao, D., & Strotmann, A. (2015). Analysis and visualization of citation networks (Synthesis Lectures on Information Concepts, Retrieval, and Services, 7[1], 1–207). Morgan & Claypool Publishers. https://doi.org/10.2200/S00664ED1V01Y201502ICR039 DOI: https://doi.org/10.1007/978-3-031-02291-3_5

Promyslov, V. G., Semenkov, K. V., & Shumov, A. S. (2014). A clustering method of asset cybersecurity classification. IFAC-PapersOnLine, 52(13), 928–933. https://doi.org/10.1016/j.ifacol.2014.11.320 DOI: https://doi.org/10.1016/j.ifacol.2019.11.313

Millar, K., Cheng, A., Chew, H. G., & Lim, C. C. (2015). Operating system classification: A minimalist approach. In Proceedings of the 2015 International Conference on Machine Learning and Cybernetics (ICMLC) (pp. 143–150). https://doi.org/10.1109/ICMLC48188.2015.9209806 DOI: https://doi.org/10.1109/ICMLC51923.2020.9469571

Aksoy, A., & Gunes, M. H. (2014). Automated IoT device identification using network traffic. In IEEE International Conference on Communications (ICC) (pp. 1–7). https://doi.org/10.1109/ICC.2014.8761821 DOI: https://doi.org/10.1109/ICC.2019.8761559

Sivanathan, A., Gharakheili, H. H., Loi, F., Radford, A., Wijenayake, C., Vishwanath, A., & Sivaraman, V. (2018). Classifying IoT devices in smart environments using network traffic characteristics. IEEE Transactions on Mobile Computing, 18(8), 1745–1759. https://doi.org/10.1109/TMC.2018.2860676 DOI: https://doi.org/10.1109/TMC.2018.2866249

Cvitić, I., Peraković, D., Periša, M., & Gupta, B. (2016). Ensemble machine learning approach for classification of IoT devices in smart home. International Journal of Machine Learning and Cybernetics, 12(11), 3179–3202. https://doi.org/10.1007/s13042-020-01217-y DOI: https://doi.org/10.1007/s13042-020-01241-0

Cam, H. (2017). Online detection and control of malware infected assets. In IEEE Military Communications Conference (MILCOM) (pp. 701–706). https://doi.org/10.1109/MILCOM.2017.8170841 DOI: https://doi.org/10.1109/MILCOM.2017.8170869