Ensuring Application Resilience in Cyber Security with Artificial and Machine Learning
DOI:
https://doi.org/10.15662/IJRAI.2025.0802007Keywords:
Cybersecurity, Application Resilience, Artificial Intelligence, Machine Learning, Threat Detection, Anomaly Detection, Intrusion Prevention, Zero Trust Architecture, Deep Learning, Security Automation, Adversarial Attacks, Data Poisoning, Security Frameworks, Incident Response, Behavioral AnalysisAbstract
As cyber threats get more complex, application resilience is a critical concern. Conventional security solutions are useless against adaptive threats that change over time, necessitating the use of AI and machine learning technologies. AI improves cybersecurity by anticipating vulnerabilities, detecting anomalies, and automating threat response. Machine learning systems analyse massive volumes of security data to identify trends in threats, hence improving real-time responses. Deep learning, image processing, and behavioural analysis improve defence capabilities against attackers. Nonetheless, concerns about adversarial assaults and data poisoning persist. The convergence of AI with cybersecurity infrastructures such as Zero Trust Architecture (ZTA) increases resilience. This article provides an overview of AI/ML technologies in cybersecurity, including their advantages, problems, and future trends in application protection.
References
1. Smith, J., & Brown, K., "Artificial Intelligence in Cybersecurity," IEEE Transactions on Information Security, vol. 45, no. 3, pp. 231-245, 2022.
2. Patel, R., & Kumar, S., "Machine Learning Applications in Threat Detection," Journal of Cybersecurity Research, vol. 18, no. 2, pp. 145-159, 2021.
3. Lin, T., & Wu, Y., "Deep Learning for Malware Detection," Springer Advances in AI Security, pp. 89-105, 2023.
4. Chen, L., & Zhang, M., "Using CNNs for Phishing Attack Detection," Cybersecurity Journal, vol. 12, no. 4, pp. 67-82, 2020.
5. Johnson, A., "Reinforcement Learning for Cyber Defense," ACM Digital Security Review, pp. 190-202, 2022.
6. Nguyen, P., "Adversarial Attacks and Defense Mechanisms in AI Security," Elsevier AI and Cybersecurity, pp. 255-270, 2023.
7. Gupta, H., & Mehta, V., "Data Poisoning in Machine Learning Security," Journal of Security Engineering, vol. 20, no. 1, pp. 35-49, 2021.
8. Lee, R., & Kim, D., "Bias and Fairness in AI-Driven Security Systems," Cyber Ethics Review, vol. 7, no. 3, pp. 112-126, 2022.
9. Williams, M., & Torres, F., "Zero Trust Architecture in AI-Based Security," IEEE Cybersecurity Innovations, pp. 75-89, 2023.
10. Davis, C., & Wilson, J., "Enhancing Application Security with Zero Trust," Network Security Research Journal, vol. 16, no. 5, pp. 98-112, 2021.
11. Carter, B., "Secure Access Service Edge (SASE) and AI Integration," Cyber Defense Strategies, pp. 45-60, 2022.
