DSDA-IRNet: Inverted Residual Network-Based IIoT Authentication With Double-Parameter Smoothing Data Augmentation Algorithm

Given the frequently changing and potentially unreliable environment, the cost-effective authentication is essential to achieve security industrial internet of the things (IIoT) environment with dramatically enhanced communication and transportation safety. Although great success has been achieved for multi-identity authentication schemes, it depends on adequate data collection, which is particularly laborious and time-consuming, being impractical for actual IIoT applications or privacy sensitive environments. Moreover, authentication schemes based on deep learning may suffer from high complexity and excessive latency, leading to potential interruption of critical services in dynamic IIoT environments. To overcome the above challenges, this paper proposes a lightweight and robust authentication scheme, namely DSDA-IRNet, which combines inverted residual network (IRNet) and double smoothing data augmentation (DSDA) algorithm. Specifically, IRNet is proposed to achieve a balance between authentication complexity and accuracy. The DSDA significantly alleviates the overfitting and low authentication accuracy caused by scarce training data. Finally, extensive experimental evaluations based on industrial scenarios datasets are conducted to assess the detection performance and robustness of the DSDA-IRNet. Compared with the existing schemes, our results characterize the outperformance of the DSDA-IRNet in authentication accuracy and computational complexity.