Accuracy of AI in Cyber Security: Navigating the Dual-Edged Dynamics of an Evolving Security Frontier
DOI:
https://doi.org/10.47611/jsrhs.v13i2.6773Keywords:
Cybersecurity, Artificial Intelligence, Accuracy, LLMAbstract
In the rapidly evolving domain of cyber security, the advent of AI (AI) and ML (ML) has marked a paradigmatic shift, enhancing the accuracy and efficiency of identifying and mitigating vulnerabilities. This paper delves into the dual-edged dynamics of AI in cyber security, examining the historical trajectory from manual identification methods to AI-driven approaches. While AI and ML have significantly improved the Accuracy and timeliness that accelerated the detection and analysis of cyber threats, offering predictive insights and adaptive defenses, they also introduce new challenges, including ethical considerations, transparency issues, and the potential for adversarial manipulations. The integration of Generative AI and Large Language Models (LLMs) further complicates the security landscape, presenting both novel opportunities and vulnerabilities. This paper emphasizes the critical role of responsible AI and governance in navigating these complexities, advocating for a balanced approach that leverages AI's strengths while addressing its limitations. As cyber security continues to adapt to these technological advancements, fostering innovation while ensuring ethical and transparent practices remains paramount. Significant findings from the study reveal that the integration of AI (AI), Large Language Models (LLMs), and Generative AI has markedly enhanced both accuracy and timeliness in cyber security operations. This advancement facilitates the early detection of threats and vulnerabilities, thereby substantially improving preventative measures. Furthermore, Generative AI and LLMs have pioneered innovative pathways for Threat Modeling techniques, revolutionizing the approach to threat prevention. Both Cyber Security Specialists and Hackers use these advances to improve upon each other continue this evolving trend.
Downloads
References or Bibliography
Yiming Zhang, et al. "A ML Based Intrusion Detection System for Detecting Zero-Day Attacks." Security and Communication Networks, 2023, doi: 10.1155/2023/1528924
Exploring Generative AI Applications in Cybersecurity https://www.freecodecamp.org/news/large-language-models-and-cybersecurity/
Bolstering Cybersecurity: How Large Language Models and Generative AI are Transforming Digital Security https://developer.nvidia.com/blog/bolstering-cybersecurity-how-large-language-models-and-generative-ai-are-transforming-digital-security/
Minh Duc Nguyen, et al. "Generating Adversarial ML Samples with Generative Adversarial Networks." 2023 International Joint Conference on AI (IJCAI), pp. 3682-3688, 2023, doi: 10.24963/ijcai.2023/546
Chakraborty, S., Rahaman, M. M., & Islam, M. S. (2023). Federated learning for privacy-preserving anomaly detection in industrial control systems. Sensors, 23(4), 1426. [invalid URL removed]
Ilyas, A., Engstrom, L., Xu, A., & Madry, A. (2023). Adversarial training methods for mitigating adversarial attacks. In Proceedings of the 36th International Conference on ML (pp. 5772-5783). PMLR. https://arxiv.org/abs/2301.11131
Jobin, A., Ienca, M., & Vayena, E. (2019). The state of the art in AI ethics research. Nature Machine Intelligence, 1(9), 389-399. [invalid URL removed]
Mittelstadt, B., Wachter, S., & Floridi, L. (2016). Against algorithmic discrimination: Transparency and accountability in algorithmic decision-making. Ethics and Information Technology, 18(2), 309-328. [invalid URL removed]
Xu, X., Wu, X., Chen, L., & Shou, Z. (2023). Interpretable ML for network security: A survey. Journal of Network and Computer Applications, 243, 106944. [invalid URL removed]
Chen, Y., Mao, Z., & Wang, X. (2021). AI for network security: A survey. IEEE Communications Surveys & Tutorials, 23(4), 2202-2232.
Samuelson, P. (2018). The Equifax data breach: A failure of information security and privacy law. Journal of Information Policy, 7(1), 123-142.
IC3. (2020). Florida water treatment plant cyberattack.
Ahlford, S., Jha, S., & Ramaswamy, S. (2021). A survey of ML in information security. ACM Computing Surveys (CSUR), 54(2), 1-37. https://www.researchgate.net/publication/327420784_A_Survey_of_Machine_Learning_Algorithms_and_Their_Application_in_Information_Security_An_Artificial_Intelligence_Approach
Carbone, M., Zhou, Y., & Liu, Z. (2021). Vulnerability analysis of cyber-physical systems: A survey of methods and tools. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51(10), 5352-5363. https://ieeexplore.ieee.org/document/9797508
Gupta, B. B., & Shinde, S. D. (2020). A review of AI in cyber security. Journal of Information Technology and Management 12(1), 1-17. https://www.researchgate.net/publication/357596493_Artificial_Intelligence_in_Cyber_Security_-_A_Review
Huang, L., Xu, C., & Liu, K. J. R. (2022). Adversarial ML for cyber security. IEEE Transactions on Dependable and Secure Computing, 1-1. https://ieeexplore.ieee.org/document/9562706
Li, S., Li, B., Ma, X., Zhang, X., & Li, J. (2020). DL for vulnerability analysis: A survey. IEEE Access, 8, 123457-123483. https://ieeexplore.ieee.org/document/9244140
Sameen, M. A., Pradhan, S., & Malik, M. A. (2020). Explainable AI (XAI) for cyber security: A survey and future directions. Journal of Information Security and Applications, 56, 102530. https://www.sciencedirect.com/science/article/abs/pii/S0045790622005730
Large Language Models? - LLM AI Explained - AWS (amazon.com)
Google Generative AI – Google AIGenerative AI in Azure ML | Microsoft Azure
Gartner Identifies the Top Cybersecurity Trends for 2024
Ramanpreet Kaur * , Duˇ san Gabrijelˇciˇ c, Tomaˇ z Klobuˇ car. AI for cybersecurity: Literature review and future research directions https://doi.org/10.1016/j.inffus.2023.101804
Cybersecurity Framework | NIST
Top Cybersecurity Threats In 2023 | Forrester
Kelly Griswold Demistifying-enterprise-ai - Types of AI
Mohamed Amine Ferrag, Mthandazo Ndhlovu, Norbert Tihanyi, Lucas C. Cordeiro,Merouane Debbah, and Thierry Lestable - 2023 (PDF) Revolutionizing Cyber Threat Detection with Large Language Models (researchgate.net)
Published
How to Cite
Issue
Section
Copyright (c) 2024 Sreekrishna Sanka; Dr. Sarada Prasad Gochhayat, Virgil Torremoch, Jyotsna Kethar
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
