Advanced modelling techniques for anomaly detection: A proactive approach to database breach mitigation

Chinedu Jude Nzekwe 1, * and Christopher J Ozurumba 2

1 Department of Applied Science and Technology, North Carolina Agricultural and Technical State University, Greensboro North Carolina, USA.
2 Data Engineer, Accredible Limited. UK.
 
Research Article
International Journal of Science and Research Archive, 2024, 13(02), 2893-2909.
Article DOI: 10.30574/ijsra.2024.13.2.2511
Publication history: 
Received on 05 November 2024; revised on 14 December 2024; accepted on 16 December 2024
 
Abstract: 
The increasing sophistication of cyber threats necessitates advanced approaches to database protection, with anomaly detection emerging as a cornerstone of modern cybersecurity strategies. This paper delves into cutting-edge modelling techniques, such as neural networks and Bayesian inference, for identifying anomalies in database environments. These techniques enhance the detection of malicious activities, including SQL injection attacks, unauthorized access, and data exfiltration attempts, which traditional rule-based systems often fail to capture. Neural networks, with their ability to analyse complex patterns in large datasets, enable the identification of subtle deviations indicative of potential threats. Coupled with Bayesian inference, which calculates the probability of anomalous events based on prior knowledge, these techniques provide a robust framework for detecting irregularities in real-time. Together, they offer superior performance in distinguishing genuine threats from benign anomalies, reducing false positives and improving response times. This study also explores the synergy between advanced anomaly detection methods and existing database protection measures, such as encryption and access control. By integrating these techniques into real-time monitoring systems, organizations can create comprehensive security architectures capable of adapting to evolving threats. Case studies from industries such as finance, healthcare, and e-commerce illustrate the practical benefits of this approach, showcasing enhanced breach mitigation and minimized data loss. The paper concludes by emphasizing the necessity of adopting proactive, analytics-driven solutions in database security. Advanced modelling techniques not only improve threat detection and response capabilities but also strengthen the overall resilience of database systems in an increasingly complex cyber landscape.
 
Keywords: 
Anomaly Detection; Neural Networks; Bayesian Inference; Database Security; SQL Injection Prevention; Real-Time Threat Monitoring
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0