Novel Anomaly Detection Scheme for Cyber Physical System using C-GAN in Fog assisted IoT Environment
Ashwini Mathur, S. Anantha Babu · 2023
An Internet of Things (IoT) appears to be an innovative technology with great potential for widespread development. There has been a rise in data security issues in recent years as a consequence of various technological developments. Despite the proliferation of security precautions, criminals have learned to circumvent them. We employ a Contingently Generative Adversarial Network in our research to detect harmful online behaviour (CC-GAN). Our proposed system employs CC-GAN, which can identify novel threats, to carry out intrusion detection based on anomalies. An Internet-of-Things layer, a fog layer, as well as a cloud layer make up the whole of our proposed fog-based infrastructure. The IoT layer consists of many connected devices, and it is here that the CC-GAN receives the training data it needs to learn to recognise potential security breaches. A convolutional neural network & encoder are trained on the cloud layer, where additional computing takes place. Adding a fog layer might help decrease the delay. Finally, the attack detection score is evaluated. For this exercise, we use the network simulator version 2.6. (NS 3.26). The simulation result shows that the proposed system achieves a higher detection rate than the state-of-the-art systems.