Impact of Artificial Intelligence in various phases of Cyber Security: A Comprehensive Survey
DOI:
https://doi.org/10.63282/3050-922X.ICAILLMBA-120Keywords:
Cyber Security, Artificial Intelligence, Detection, Response, Recovery, Cyber-AttacksAbstract
Artificial Intelligence which is a powerful technology has a great impact in many of the cybersecurity tasks like detection of new attacks, predictive intelligence, threat detection, AI enabled cyber defense etc. AI enhanced detections are quite useful to have high accuracy in threat detection and response which strengthens the cybersecurity teams to automate the security issues & attacks and to accelerate the process of detection. Identification of threats accurately is crucial especially if the threat is AI generated, where the attackers can automate and create sophisticated malware, it can be a complicated task. This study offers a comprehensive review of various AI methods useful in different phases of Cyber Security and an insight into AI enabled Cyber-attacks. The AI methods and their functionality is compared to learn how well they perform in mitigating the risks of cyber security at various phases. The study provides clear understanding of the impact of AI on cybersecurity in automation, reinforced cyber defense and intelligence in threat detection. This study emphasizes the use of AI tools for employee training used in threat detection that mitigate the risks of cyber-attacks. In all the phases of Cyber Security we need continuous monitoring and frequent vigilance for breaches and threats which require the involvement of AI tools. A thorough understanding of the life cycle of Cyber Security and various AI tools involved in each phase is mentioned in this work as a comprehensive study.
References
[1] NIST CSF https://en.wikipedia.org/wiki/NIST_Cybersecurity_Framework
[2] The NIST Cybersecurity Framework (CSF) 2.0. National Institute of Standards and Technology,Gaithersburg,MD,NIST CSWP 29. https://doi.org/10.6028/NIST.CSWP.29
[3] Buczak, A. L., & Guven, E. (2016).A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection. IEEE Communications Surveys & Tutorials, 18(2), 1153–1176.
[4] NIST AI RMF https://doi.org/10.6028/NIST.AI.600-1
[5] NIST ARIA https://ai-challenges.nist.gov/aria
[6] NIST ARIA 0.1 Pilot evaluation https://ai-challenges.nist.gov/aria/docs/evaluation_plan.pdf
[7] Sommer, R., & Paxson, V. (2010). Outside the Closed World: On Using Machine Learning for Network Intrusion Detection.IEEE Symposium on Security and Privacy.
[8] AI RMF GAI profile https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf
[9] AI Risks www.gov.uk/government/publications/international-scientific-report-on-the-safety-of-advanced-ai
[10] Ibrahim, A., Valli, C., McAteer, I. et al. A security review of local government using NIST CSF: a case study., J Supercomput 74, 5171–5186 (2018).
[11] Y. Fan, H. Li, S. Li, and K. Huang, Cyber Asset Identification Based on Network Behavior Analysis,IEEE
[12] J. Liu, L. Yang, and Q. Zhao ,Dynamic Cyber Asset Management Using AI for Threat Detection ,IEEE Transactions on Network and Service Management, 2021
[13] https://www.gartner.com/en/articles/how-ai-is-redefining-cybersecurity
[14] https://www.technologyreview.com/2021/04/22/1023623/ai-cybersecurity/
[16] Security Information and Event Management (SIEM) – https://www.gartner.com
[17] OSINT and Reconnaisance https://www.webasha.com/blog/ai-driven-osint-reconnaissance-how-artificial-intelligence-is-transforming-cyber-intelligence-and-threat-detection
