Study of scale-free structures in feed-forward neural networks against backdoor attacks

Abstract

Due to the computational complexities of artificial neural networks, MLaaS (machine learning as a service), which is one of the main cloud computing services, is taking the responsibility of the neural network training. With the increase in demand for third-party neural network training, there is a high possibility of adversarial attacks through malicious training. Backdoor attacks are among the most efficient attacks which cause targeted misclassification while the accuracy on clean data is not affected. In this paper, we provide the first investigation about the influence of applying scale-free networks to feed-forward neural networks (FFNNs) against backdoor attacks inserted via the MNIST dataset. It is the first time that the feed-forward neural network structure is changed to improve the network robustness against backdoor attacks using scale-free structure before the network is getting attacked. It has been achieved that scale-free neural networks with long range connections not only keep the accuracy high with strong stability but also make it independent of the number of hidden layers and prevent overfitting.