International Journal of Scientific Research and Engineering Development

Malware detection is the process of identifying malicious software such as viruses, worms, trojans, spyware, and ransomware that harm devices or steal sensitive information. It works by examining files, programs, system behavior, or network activity to spot unusual or unsafe patterns. The goal of malware detection is to prevent unauthorized access, data loss, and system damage by quickly identifying harmful activity and blocking its execution. A major traditional issue in malware detection is poor adaptability. To address this issue, this project proposes a hybrid cybersecurity model for malware detection using convolutional neural networks (CNNs) and random forest classifiers. The system combines deep learning and machine learning techniques to improve detection accuracy and efficiency.

Shifa Bilal Tamboli, Simeen Phiroj Mulani, Arman Tajuddin Shiakh,"A Hybrid Cybersecurity Model for Malware Detection Using Convolutional Neural Networks and Random Forest Classifiers" International Journal of Scientific Research and Engineering Development, V9(2): Page(2195-2201) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.