Citation:

Rahul Gupta, 2022. "Artificial Intelligence in Cybersecurity: From Automated Threat Hunting to Self-Healing Networks", ESP Journal of Engineering & Technology Advancements, 2(4): 92-104.

Abstract:

Artificial Intelligence (AI) is advancing aggressively as a force multiplier in cybersecurity and threatening intelligence. This paper concerns the use of AI in cybersecurity, with a close look at automated threat-hunting and self-healing networks. Automated threat hunting is the action whereby the system looks for threats by itself without the need of the system administrator, and the AI uses machine learning algorithms to analyze data and look for indicators of compromise that could be a sign of an attack. A self-healing network is another type of network that is completely powered by artificial intelligence, making it possible to detect and fix weaknesses on its own and without relying on man’s services. Due to the complications of cybercrimes, security and precautions have become more complex so as to accommodate the new complexities. Conventional practices that depend on people’s actions are mostly ineffective, slow, and even reactive, through which systems remain exposed to violations. AI-oriented cybersecurity, in turn, provides a more effective one, concrete of which is monitoring and intervention. Because machine learning models are developed in large databases, such models are able to detect new types of threats and the appearance of new methods of attack. The very nature of threats changes from time to time, and new exploits and vulnerabilities are found on a daily basis, hence the need for such an approach. This paper also explores issues related to AI in the context of cybersecurity. Granted, AI has several benefits that cannot be disputed; however, there are its limitations as well. More data is needed in algorithms, and the vulnerability of deep learning models to attacks, etc., are considered here. In addition, the discussion of ethical issues of using AI in cybersecurity, such as privacy and weaponization of AI, is also discussed. Describing the procedures of creating and applying AI technologies in the cybersecurity context, an author outlines machine learning, neural networks, and deep learning. What it demonstrates is that AI excels at saving the time needed to learn and act on threats while growing a network’s security. To examine this cross-sectional study, will endeavor to compare the usage of AI-based cybersecurity against the other conventional types of cybersecurity and the outcomes. Hence, it can be stated that by using AI, the approaches to cybersecurity can be enhanced significantly to offer more flexible, elaborate and enhanced levels of security. The problems connected with the use of AI in cybersecurity should be solved, and the usage of AI in cybersecurity should be controlled and safe. Therefore, the paper includes a systematically organized detailed analysis of the state of artificial intelligence in the cybersecurity area and several forecasts of the tendencies for AI in the cybersecurity sphere, which is further complicating.

References:

[1] Doshi-Velez, F., & Kim, B. (2017). “Towards a rigorous science of interpretable machine learning.” Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning.

[2] Hodge, V. J., & Austin, J. (2004). “A survey of outlier detection methodologies.” Artificial Intelligence Review, 22(2), 85-126.

[3] Lin, W. H., Lin, H. C., Wang, P., Wu, B. H., & Tsai, J. Y. (2018, April). Using convolutional neural networks to network intrusion detection for cyber threats. In 2018 IEEE International Conference on Applied System Invention (ICASI) (pp. 1107-1110). IEEE.

[4] Barocas, S., & Selbst, A. D. (2016). “Big Data’s Disparate Impact.” California Law Review, 104(3), 671-732.

[5] Caruana, R., Gehrke, J., Koch, P., & Nair, V. (2015). “Intelligible Models for Healthcare: Predicting Pneumonia Risk and Hospital 30-Day Readmission.” Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1721-1730.

[6] McCool, M., Reinders, J., & Robison, A. (2012). Structured parallel programming: patterns for efficient computation. Elsevier.

[7] Sculley, D., Holt, J., Golovin, D., & others (2015). “Hidden Technical Debt in Machine Learning Systems.” Proceedings of the 28th International Conference on Neural Information Processing Systems, 2503-2511.

[8] Sarker, I. H., Furhad, M. H., & Nowrozy, R. (2021). AI-driven cybersecurity: an overview, security intelligence modeling and research directions. SN Computer Science, 2(3), 173.

[9] Nasteski, V. (2017). An overview of the supervised machine learning methods. Horizons. b, 4(51-62), 56.

[10] Wiering, M. A., & Van Otterlo, M. (2012). Reinforcement learning. Adaptation, learning, and optimization, 12(3), 729.

[11] Nielsen, M. A. (2015). Neural networks and deep learning (Vol. 25, pp. 15-24). San Francisco, CA, USA: Determination press.

[12] Suk, H. I. (2017). An introduction to neural networks and deep learning. In Deep Learning for Medical Image Analysis (pp. 3-24). Academic Press.

[13] Sarker, I. H., Furhad, M. H., & Nowrozy, R. (2021). Ai-driven cybersecurity: an overview, security intelligence modeling and research directions. SN Computer Science, 2(3), 173.

[14] Priyadarshini, I., & Cotton, C. (2022). Cybersecurity: Ethics, legal, risks, and policies. Apple Academic Press.

[15] AI in cybersecurity: A double-edged sword, deloitte, online. https://www2.deloitte.com/xe/en/pages/about-deloitte/articles/securing-the-future/ai-in-cybersecurity.html

[16] Guadagno, L., Naddeo, C., Raimondo, M., Barra, G., Vertuccio, L., Sorrentino, A., & Kadlec, M. (2017). Development of self-healing multifunctional materials. Composites Part B: Engineering, 128, 30-38.

[17] Artificial Intelligence and Cybersecurity, trellix, online. https://www.trellix.com/security-awareness/cybersecurity/artificial-intelligence-and-cybersecurity/

[18] Machine Learning and Artificial Intelligence in Cyber Security: Automating Defence, cdsec, online. https://www.cdsec.co.uk/blog/machine-learning-and-artificial-intelligence-in-cyber-security-automating-defence

[19] Piyush Ranjan, 2022.”Fundamentals Of Digital Transformation In Financial Services: Key Drivers and Strategies”, International Journal of Core Engineering & Management, Volume 7, Issue 3, PP 41-50, [Link]

Keywords:

Artificial Intelligence (AI), Cybersecurity, Automated Threat Hunting, Self-Healing Networks, Machine Learning (ML), Neural Networks.