The objective of this research is to enhance malware analysis and digital forensics by integrating artificial intelligence and blockchain technology. Traditional forensic systems often fail to detect modern malware due to their static nature and limited adaptability. Our proposed framework employs machine learning techniques, including the random forest algorithm, to classify malware based on static and dynamic analysis. We utilize publicly available malware datasets, preprocessing them for feature extraction using Scikit-learn, and train AI models to detect threats efficiently. The trained AI module achieves an accuracy of 96.5%, with a precision of 94.8%, a recall of 95.2%, and an F1-score of 95.0%, significantly outperforming traditional signature-based methods. To ensure integrity and traceability, we implement a private Ethereum blockchain, enabling secure, immutable storage of forensic evidence. Security aspects, including potential vulnerabilities such as 51% attacks, Sybil attacks, and smart contract vulnerabilities, are addressed through multi-factor authentication, periodic consensus validation, and secure cryptographic hashing. The system architecture includes an AI-driven threat detection component, a decentralized blockchain ledger for evidence preservation, and a visualization layer using Matplotlib. Empirical evaluation demonstrates improved detection rates and enhanced security in malware forensics.