Behavior-Based DDoS Detection for Multi-Vector Attacks in Hybrid Cloud Environments

Tirumala Ashish Kumar Manne

Abstract: Distributed Denial of Service (DDoS) attacks are becoming increasingly sophisticated, leveraging multi-vector strategies that target vulnerabilities in hybrid cloud environments. Traditional signature-based detection mechanisms struggle to keep pace with evolving attack patterns, necessitating behavior-based approaches that analyze network traffic and system anomalies. This paper presents a behavior-based DDoS detection framework that utilizes machine learning and anomaly detection techniques to identify and mitigate multi-vector attacks in hybrid cloud environments. The proposed solution enhances threat detection accuracy, reduces false positives, and improves response time by leveraging real-time traffic analytics, predictive modeling, and adaptive defense mechanisms. Experimental results demonstrate the efficacy of the framework in identifying complex attack patterns and mitigating their impact on cloud infrastructure.

Keywords: DDoS Detection, Multi-Vector Attacks, Hybrid Cloud Security, Anomaly Detection, Cloud Computing Security

How to Cite?: Tirumala Ashish Kumar Manne, "Behavior-Based DDoS Detection for Multi-Vector Attacks in Hybrid Cloud Environments", Volume 12 Issue 3, March 2023, International Journal of Science and Research (IJSR), Pages: 1874-1877, https://www.ijsr.net/getabstract.php?paperid=SR23307113426, DOI: https://dx.doi.org/10.21275/SR23307113426