Industrial IoT (IIoT) system security becomes crucial as enterprises use IoT technologies to improve efficiency, productivity, and automation. IoT devices in industrial environments create additional attack surfaces and weaknesses, making them ideal targets for unscrupulous actors. IIoT malware assaults can interrupt production, breach data, and harm physical infrastructure. Predicting and combating IIoT malware threats is difficult. Signature-based malware detection is used in traditional IIoT security systems to identify and stop threats. Detecting new malware strains is limited by this method. Signaturebased solutions may also struggle in complicated IIoT contexts due to their static nature. IIoT's realtime operation needs and resource limits make security implementation difficult without affecting system performance. This project creates a cutting-edge IIoT malware prediction system. The proposed model's proactive and adaptive security is important. The technology uses advanced machine learning and classification to scan device and network traffic in real time and discover malware anomalies. This proactive strategy detects and mitigates risks early, avoiding industrial disruptions and protecting critical data