Analysis of Distributed Denial-of-Service Attacks in Cyber Forensics

Distributed Denial of Service (DDoS) attacks are among the most serious threats to modern digital infrastructure, with consequences that can significantly impact the security, trust, and stability of critical systems. Effectively countering these attacks requires an approach beyond traditional methods and the adoption of advanced cyber forensics tools. This study introduces an innovative framework built upon the integration of big data analytics, machine learning algorithms, and established digital forensics standards. The framework enables precise attacker identification, protection of digital evidence, and scalable management of large-scale data. Designed based on the NIST methodology, distributed processing using Hadoop, and advanced machine learning models such as Gradient Boosting and Random Forest, the framework offers key contributions, including a scalable architecture for real-time traffic analysis, a legal layer for safeguarding digital evidence, and precise mechanisms for tracking spoofed addresses. The findings of this research demonstrate that the proposed approach can address gaps in conventional methods and provide an efficient solution for the analysis and management of modern cyber attacks.