Multi-Level Intrusion Detection and Log Management System in Cloud Computer

Authors- Okoni E. Bennett, Ernest O. Amadi

Abstract-This journal addresses critical security challenges in cloud computing, such as management complexities, data falsification, unauthorized access, and advanced evasion techniques, proposing a Multi-Level Intrusion Detection and Log Management System (ML-IDS) leveraging Behavioral Traffic Analysis Techniques to enhance security, scalability, and performance. The system integrates a Cloud Management Platform (CMP) for efficient resource allocation and monitoring, ensuring optimal performance while maintaining security, and employs Deep Packet Inspection (DPI) for real-time traffic analysis, enabling the identification of malicious activities at a granular level. Additionally, it incorporates a Multi-Tier Temporal Traffic Analysis (MTTTA) module to detect anomalies by analyzing patterns across different timeframes, improving detection accuracy and reducing false alarms. The robust log management component provides secure storage, correlation, and analysis of event logs, offering actionable insights into potential security breaches. Experimental results demonstrate the system’s effectiveness, achieving a high detection rate of 90.00%, a low false-positive rate of 5.00%, and faster response times compared to traditional approaches. The ML-IDS exhibits exceptional scalability and adaptability, making it suitable for real-time protection of dynamic and diverse cloud infrastructures. This innovative solution not only bridges critical security gaps in cloud environments but also enhances the overall reliability and resilience of cloud ecosystems by providing a multi-layered approach to intrusion detection and log management. The results highlight the potential of the proposed system to redefine security benchmarks and establish a robust framework for mitigating emerging threats in cloud-based infrastructures.

DOI: /10.61463/ijset.vol.13.issue1.134