A Hybrid Machine Learning–Deep Learning Framework for Explainable and Scalable Digital Forensic Analysis

The intensive development of new digital technologies, cloud computing, and networked systems made the amount and complexity of the digital evidence in cases of cybercrime investigation significantly greater. Manual and rule-based digital forensic techniques cannot manage large-scale heterogeneous and real-time data environments. Such systems are not always scalable, interpretable, and robust, which restricts their applicability in the current cyber threats. To address these issues, this paper suggests a Hybrid AI-Based Forensic Intelligence Framework that could be used to analyze digital evidence in scales and provide an explanation and real-time analysis. The suggested framework will combine some of the latest methods of artificial intelligence, such as machine learning, deep learning, and explainable artificial intelligence (XAI), to automate and improve the process of forensics. It helps in preprocessing data, feature extractions, anomaly detection, correlation of evidence and transparent decision making. The system can effectively handle a wide range of sources of data including system logs, network traffic, and multimedia artifacts using scalable hybrid models. Also, explainability properties provide legal reliability and transparency of forensic results. The experimental findings indicate that there are better accuracy, scalability, and reliability as opposed to traditional tools and single-model solutions. On the whole, the framework offers a powerful and intelligent approach to digital forensics in the modern context related to the investigation and making decisions more efficient in a complex cybercrime situation. Keywords: cybersecurity; artificial intelligence; machine learning; explainable AI; Digital Forensics; Real-Time Evidence Analysis; Forensic Intelligence Framework