A Review on AI in Cybersecurity Threat Detection and Response Using CNN

Cybersecurity has become one of the most critical global concerns as cyberattacks grow in scale, diversity, and sophistication. Traditional security systems based on signatures and manual rule definitions are unable to detect newly emerging and zero-day threats. Recent advances in Artificial Intelligence (AI) and Deep Learning (DL) have shown promising results in automating threat detection. Convolutional Neural Networks (CNN), known for their superior feature extraction capability, are widely used for malware classification, intrusion detection, phishing analysis, and anomaly detection. CNNs can automatically learn spatial–temporal patterns from network traffic, system logs, and binary malware images without manual feature engineering. This review presents a detailed analysis of CNN-based methods for cybersecurity threat detection and response, highlights major research findings, identifies limitations, and discusses future directions.