A PREDICTIVE MACHINE INTELLIGENCE MODEL FOR MOBILE MALWARE FORECASTING

The rapid growth of internet usage and online services has significantly increased the number of malicious websites, phishing attacks, and visually deceptive online content. Traditional security systems rely on signature-based detection methods, which are often ineffective in identifying newly emerging and visually modified threats. To address this limitation, this paper proposes an image-based predictive machine intelligence model for malware and phishing detection.The system analyzes webpage images provided by users and classifies them into Safe, Malicious, Hackware, or Benign categories. Convolutional Neural Networks (CNN) are used to extract visual features such as layout structures, text regions, and interface patterns from webpage screenshots. Recurrent Convolutional Neural Networks (RCNN) are employed to analyze complex patterns and improve detection accuracy.By combining CNN and RCNN, the model learns distinguishing visual characteristics of malicious interfaces. The proposed system is efficient, scalable, and suitable for real-time deployment, providing an effective solution for detecting visually deceptive cyber threats and enhancing overall online security.