@

초록

With the proliferation of cloud computing, the need for advanced security measures in the cloud has become critical. Traditional malware detection methods, which are often limited to single-tier approaches, have become increasingly inadequate against evolving cyber threats. This research presents a comprehensive 3-tier malware detection framework explicitly designed for cloud computing environments. This system integrates data classification, behavioral analysis, and heuristic techniques to provide a multi-layered defense mechanism. The first tier, data classification, uses machine learning models to categorize incoming data and flag potential threats. The second, behavioral analysis, monitors complex data interactions and captures unusual patterns that indicate malware activity. The final tier, heuristics, refines the detection process using expert-driven rules derived from historical malware data. Together, these tiers provide enhanced security against both known malware and emerging zero-day threats. The findings in this paper provide a blueprint for a future where cloud environments can be more resilient and secure against malicious activity. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

키워드