The Industrial Internet of Things (IIoT) platform consists of purpose-driven communication controllers, enterprise-grade modems (routers and gateways), and edge computing systems that require integrated software and sensing capability in mission-critical environments. Extensible purpose-built industrial supervisory control and data acquisition networks are prone to numerous cybersecurity threats. In this paper, the historical databased qualitative threat assessment was part of the comprehensive risk breakdown (i.e., to quantify assessment and remediation) of the practicing industry (i.e., systems that rely on robotics, big data & analytics). Furthermore, a risk and operability (HAZOP & convolution neural-network) evaluation was proved to be the paramount study for autonomous vulnerability assessment. Through autonomous network management, continuous software monitoring, data-driven device insights, and integrated content filtering, the proposed endpoint protection scheme shows significant improvement in preventing data breaches, denial of service (DoS), and malware detection. A distinctive computational methodology to determine the cyber risk for industrial structures with IoT-explicit control factors has been programmed and elucidated in the perspective of IIoT systems. Firmware driven emulation (integrated and optimized) outcome aided to reduce breach ratio, better incident detection, and enhanced protection of confidential data.
- Convolution neural-network
- HAZOP analysis
- Hybrid integrity model
- Industrial Internet of Things
- Multicriteria decision analysis