Deep Learning-Driven Compliance Automation for Continuous Monitoring of Security Controls in Regulated Cloud Systems
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V1I3P104Keywords:
Deep Learning, Compliance Automation, Continuous Monitoring, Cloud Security, Security Controls, Anomaly Detection, Risk ScoringAbstract
The adoption of cloud computing in regulated industries like in healthcare, finance and government has escalated the necessity of continuous compliance verification of security controls. Conventional compliance controls are based on periodic auditing and validation tools that are rule based and not dynamic enough to meet the large scale cloud infrastructures. The solution is that such approaches tend to yield slow detection, excessive false positive rate, and poor contextual recognition. This paper attempts to provide Deep Learning-powered Compliance Automation architecture to monitor security controls in regulated cloud systems continuously. The suggested architecture combines the multi-source telemetry, such as cloud logs, configuration states, identity records, and policy metadata, into a single pipeline of analytical processing. High quality deep learning models such as LSTM based sequence learning, convolutional feature learning and transformer based semantic analysis are used to identify anomalies, configuration drift and control violation by regulations in real-time. High-level regulatory requirements are translated into machine-readable rules by a control mapping and policy encoding mechanism and the detected violations are prioritized in a dynamic risk scoring module depending on their severity and compliance impact. Experimental analysis has shown a better detection rate, false positives have been minimized, and real-time monitoring is more efficient as opposed to conventional rule-driven systems. The framework contains scalable, adaptive and regulation conscious compliance management in multi-cloud environment. The study demonstrates that deep learning can transform the compliance assurance system to ensure security governance within the contemporary cloud infrastructure.
References
[1] Du, M., Li, F., Zheng, G., & Srikumar, V. (2017, October). Deeplog: Anomaly detection and diagnosis from system logs through deep learning. In Proceedings of the 2017 ACM SIGSAC conference on computer and communications security (pp. 1285-1298).
[2] Lin, A., & Chen, N. C. (2012). Cloud computing as an innovation: Percepetion, attitude, and adoption. International journal of information management, 32(6), 533-540.
[3] Wu, Y. U. N., Cegielski, C. G., Hazen, B. T., & Hall, D. J. (2013). Cloud computing in support of supply chain information system infrastructure: understanding when to go to the cloud. Journal of supply chain management, 49(3), 25-41.
[4] Abassi, R., & El Fatmi, S. G. (2008, September). An Automated Validation Method for Security Policies: the firewall case. In 2008 The Fourth International Conference on Information Assurance and Security (pp. 291-294). IEEE.
[5] Desnitsky, V., & Kotenko, I. (2016). Automated design, verification and testing of secure systems with embedded devices based on elicitation of expert knowledge. Journal of ambient intelligence and humanized computing, 7(5), 705-719.
[6] Jiang, H., Nagra, J., & Ahammad, P. (2016). SoK: Applying machine learning in security – A survey. arXiv Preprint arXiv:1611.03186.
[7] Kshetri, N. (2013). Privacy and security issues in cloud computing: The role of institutions and institutional evolution. Telecommunications Policy, 37(4-5), 372-386.
[8] Bamberger, K. A. (2009). Technologies of compliance: Risk and regulation in a digital age. Tex. L. Rev., 88, 669.
[9] Xia, M., Li, T., Zhang, Y., & De Silva, C. W. (2016). Closed-loop design evolution of engineering system using condition monitoring through internet of things and cloud computing. Computer Networks, 101, 5-18.
[10] Joshi, K. P., Elluri, L., & Nagar, A. (2020). An integrated knowledge graph to automate cloud data compliance. Ieee Access, 8, 148541-148555.
[11] Wu, J., Chen, X. Y., Zhang, H., Xiong, L. D., Lei, H., & Deng, S. H. (2019). Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology, 17(1), 26-40.
[12] Andonie, R. (2019). Hyperparameter optimization in learning systems. Journal of Membrane Computing, 1(4), 279-291.
[13] Ruiter, J., & Warnier, M. (2011). Privacy regulations for cloud computing: Compliance and implementation in theory and practice. In Computers, privacy and data protection: an element of choice (pp. 361-376). Dordrecht: Springer Netherlands.
[14] Jawed, M. (2019). Continuous security in DevOps environment: Integrating automated security checks at each stage of continuous deployment pipeline (Doctoral dissertation, Wien).
[15] Lin, X., Wang, P., & Wu, B. (2013, November). Log analysis in cloud computing environment with Hadoop and Spark. In 2013 5th IEEE International conference on broadband network & multimedia technology (pp. 273-276). IEEE.
[16] Roy, S., DeLoach, J., Li, Y., Herndon, N., Caragea, D., Ou, X., ... & Guevara, N. (2015, December). Experimental study with real-world data for android app security analysis using machine learning. In Proceedings of the 31st Annual Computer Security Applications Conference (pp. 81-90).
[17] Cinque, M., Esposito, C., & Pecchia, A. (2019). Security log analysis in critical industrial systems exploiting game theoretic feature selection and evidence combination. IEEE Transactions on Industrial Informatics, 16(6), 3871-3880.
[18] Chen, H., Tu, S., Zhao, C., & Huang, Y. (2016, May). Provenance cloud security auditing system based on log analysis. In 2016 IEEE International Conference of Online Analysis and Computing Science (ICOACS) (pp. 155-159). IEEE.
[19] Papanikolaou, N., Pearson, S., Mont, M. C., & Ko, R. K. (2014). A toolkit for automating compliance in cloud computing services. International Journal of Cloud Computing 2, 3(1), 45-68.
[20] Fernández, A., García, S., Luengo, J., Bernadó-Mansilla, E., & Herrera, F. (2010). Genetics-based machine learning for rule induction: state of the art, taxonomy, and comparative study. IEEE Transactions on Evolutionary Computation, 14(6), 913-941.
[21] Soares, E., Angelov, P. P., Costa, B., Castro, M. P. G., Nageshrao, S., & Filev, D. (2020). Explaining deep learning models through rule-based approximation and visualization. IEEE Transactions on Fuzzy Systems, 29(8), 2399-2407.
