Malware Detection and Analysis Using Deep Learning Through Fully Connected Neural Network (FCNN)

This research focuses on malware detection and analysis using deep learning techniques through Fully Connected Neural Network (FCNN) to enhance detection accuracy and reduce false alarm rates. The study emphasizes developing a model capable of efficiently detecting malware attacks in complex network environments. The model utilizes features including Source IP, Destination IP, Protocol, Source Port, and Packet Size for prediction. Experimental results demonstrate the FCNN model's high performance in data classification, achieving 91.49% Accuracy, 95.45% Precision, 87.50% Recall, and 91.18% F1-score. The research highlights the potential of deep learning technology in cybersecurity threat prevention and handling complex attacks, providing effective and timely responses to emerging attack patterns.