Security Policy Updates with Reinforcement Learning
Keywords:
Reinforcement learning, SD-WAN, real-time security, Deep Q-NetworksAbstract
Commercial networking is changed by SD-WANs' Policy driven administration and improved distributed network performance. The changing threat landscape makes it hard to maintain necessary security protocol that can handle the real time incoming threats. The new real time security policy change is possible by reinforced learning capability, which helps in increasing adaptability of SD-WAN thread detection, response and resource efficiency. The objective of this paper is to study the Deep Q-Networks and actor critic model for dynamic policy updates which is used in reinforced learning to improve the security management of SD-WAN.
Downloads
References
Feamster, N., Rexford, J., & Zegura, E. (2014). "The road to SDN: An intellectual history of programmable networks." ACM SIGCOMM Computer Communication Review, 44(2), 87-98.
Anderson, R. (2021). Security Engineering: A Guide to Building Dependable Distributed Systems. Wiley.
Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction. MIT Press.
Mnih, V., et al. (2015). "Human-level control through deep reinforcement learning." Nature, 518(7540), 529-533.
S. Kumari, “AI-Driven Cloud Transformation for Product Management: Optimizing Resource Allocation, Cost Management, and Market Adaptation in Digital Products ”, IoT and Edge Comp. J, vol. 2, no. 1, pp. 29–54, Jun. 2022
S. Kumari, “Agile Cloud Transformation in Enterprise Systems: Integrating AI for Continuous Improvement, Risk Management, and Scalability”, Australian Journal of Machine Learning Research & Applications, vol. 2, no. 1, pp. 416–440, Mar. 2022
Zhu, Yue, and Johnathan Crowell. "Systematic Review of Advancing Machine Learning Through Cross-Domain Analysis of Unlabeled Data." Journal of Science & Technology 4.1 (2023): 136-155.
Sangaraju, Varun Varma, and Senthilkumar Rajagopal. "Applications of Computational Models in OCD." In Nutrition and Obsessive-Compulsive Disorder, pp. 26-35. CRC Press.
Sivaraman, Hariprasad. "Self-Healing Test Automation Frameworks Using Reinforcement Learning for Full-Stack Test Automation." Journal of Artificial Intelligence & Cloud Computing. SRC/JAICC-E210. DOI: doi. org/10.47363/JAICC/2022 (1) E210 J Arti Inte & Cloud Comp 1.4 (2022): 2-4.
Singu, Santosh Kumar. "Impact of Data Warehousing on Business Intelligence and Analytics." ESP Journal of Engineering & Technology Advancements 2.2 (2022): 101-113.
S. Kumari, “AI-Enhanced Agile Development for Digital Product Management: Leveraging Data-Driven Insights for Iterative Improvement and Market Adaptation”, Adv. in Deep Learning Techniques, vol. 2, no. 1, pp. 49–68, Mar. 2022
S. Kumari, “AI-Driven Cybersecurity in Agile Cloud Transformation: Leveraging Machine Learning to Automate Threat Detection, Vulnerability Management, and Incident Response”, J. of Art. Int. Research, vol. 2, no. 1, pp. 286–305, Apr. 2022
Sangaraju, Varun Varma, and Kathleen Hargiss. "Zero trust security and multifactor authentication in fog computing environment." Available at SSRN 4472055.
Sivaraman, Hariprasad. (2022). Adaptive Thresholding in ML-Driven Alerting Systems for Reducing False Positives in Production Environments. INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 6. 10.55041/IJSREM11938.
S. Kumari, “Cybersecurity in Digital Transformation: Using AI to Automate Threat Detection and Response in Multi-Cloud Infrastructures ”, J. Computational Intel. & Robotics, vol. 2, no. 2, pp. 9–27, Aug. 2022
Sivaraman, Hariprasad. "Behavior-Based DDoS Detection for Multi-Vector Attacks in Hybrid Cloud Environments." Sivaraman H. Behavior-Based DDoS Detection for Multi-Vector Attacks in Hybrid Cloud Environments.
Papernot, N., et al. (2018). "Technical challenges of machine learning in cybersecurity." ACM Computing Surveys, 51(3), 65.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Howard, M., & LeBlanc, D. (2020). Writing Secure Code. Microsoft Press.
Silver, D., et al. (2017). "Mastering the game of Go with deep neural networks and tree search." Nature, 550(7676), 354-359.
