Secure Data Warehousing in ERP Environments: An AI-Based Multimodal Threat Detection Framework
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V5I3P111Keywords:
ERP Security, Data Warehousing, AI-based Threat Detection, Multiform Learning, Anomaly Detection, Cybersecurity, Enterprise Data ProtectionAbstract
Enterprise Resource Planning (ERP) systems are considered the foundation of contemporary organizations and combine financial, operational, and human resource information in dispersed settings. With the further assimilation of cloud-based and hybrid ERP architectures by business entities, data warehouses forming the basis of entities are experiencing an increasing number of security risks due to internal threat activity, data access, and advanced hacking exploiting non-homogeneous flows of data. Conventional rule-based or single-model security frameworks may not offer the opportunity to detect the presence of complex, multi-vector attacks in time, which dynamically change in the ERP ecosystem. To solve these pitfalls, this paper has come up with an AI-powered Multimodal Threat Detection Framework that is exclusively used in a secure ERP data warehousing context. The framework unifies various modalities of data such as user behavior analytics, access control logs, network telemetry and transactional metadata with single deep learning framework that builds on the principles of attention-based feature fusion and adaptive anomaly scoring. The experimental assessments of the simulated ERP data sets prove that the offered model performs better than the traditional machine learning baselines in terms of better preciseness of detecting and lowering the false-positive ratios. The findings show the promise of multimodal intelligence to improve situational awareness, adaptable reaction, and information security in business settings. The framework offers a scalable basis on real-time threats handling and assist on adherence to security and governance norms throughout built ERP ecosystems
Downloads
References
[1] Santos, R. J., Bernardino, J., & Vieira, M. (2011, April). A survey on data security in data warehousing: Issues, challenges and opportunities. In 2011 IEEE EUROCON-International Conference on Computer as a Tool (pp. 1-4). IEEE.
[2] Saa, P., Cueva Costales, A., Moscoso-Zea, O., & Luján-Mora, S. (2017). Moving ERP systems to the cloud-data security issues.
[3] Madhavram, C., Galla, E. P., Sunkara, J. R., Rajaram, S. K., & Patra, G. K. (2022). AI-Driven Threat Detection: Leveraging Big Data For Advanced Cybersecurity Compliance. Available at SSRN 5029406.
[4] Kim, A., Oh, J., Ryu, J., & Lee, K. (2020). A review of insider threat detection approaches with IoT perspective. IEEE Access, 8, 78847-78867.
[5] Wang, L. (2017, August). Heterogeneous data and big data analytics. In ACIS (Vol. 3, No. 1, pp. 8-15).
[6] Boppana, S. B., Moore, C. S., Bodepudi, V., Jha, K. M., Maka, S. R., & Sadaram, G. (2021). AI And ML Applications In Big Data Analytics: Transforming ERP Security Models For Modern Enterprises.
[7] Smith, Anne Marie. (2002, April). Data Warehousing & ERP – A Combination of Forces. TDAN.com. This article discusses the intersection of ERP systems and data warehousing, including challenges of integration.
[8] Ponniah, Paul R. (2001). Data Warehousing Fundamentals for IT Professionals. (Chapter: “Integrating ERP and Data Warehouse”). This book section describes how ERP data is integrated into data warehouses.
[9] Mishra, Rishit. (2020). “Evolution of ERP Cybersecurity.” International Journal of Engineering Research & Technology (IJERT), Vol. 9 Issue 04, April 2020.
[10] Ringsquandl, M., Lamparter, S., & Lepratti, R. (2014). “Context-Aware Analytics in MOM Applications.” arXiv preprint. This touches on heterogeneous data integration in the space of MES/MOM and ERP environments.
[11] Kumar, Naveen. (2019). “Anomaly Detection in ERP Systems Using AI and Machine Learning.” International Journal of Scientific Research in Science, Engineering and Technology (IJSRSET), Vol. 6 No. 3, pp. 522-530.
