The ever-evolving cyber threat landscape has enabled sophisticated and intelligent malware detection techniques. False positive rates and inadequate attack pattern adaptation are common limitations of conventional intrusion detection algorithms. In an effort to improve security, this work offers a combined malware detection method based on artificial intelligence. Additionally, it integrates deep learning and machine learning with blockchain technology. By using Random Forest and Long Short-Term Memory for feature selection and anomaly detection, the suggested system can identify cyber threats with greater accuracy. A blockchain ledger also facilitates the recording of attack indicators, enhancing threat intelligence. The proposed method outperformed the standalone ML/DL results with 99.7% accuracy, 99.5% precision, 99.4% recall, and a 99.5% F1-score on the chosen dataset. Blockchain technology further enhances incremental trust in security by ensuring confidence in cybersecurity agencies by eliminating data manipulation.

Cybersecurity Malware Detection Random Forest Machine Learning Blockchain