Immuno-mimetic Deep Neural Networks (Immuno-Net)
This work addresses the problem of adversarial vulnerability in deep learning for image classification, offering a novel biomimetic approach that is incremental in applying immune system concepts to neural networks.
The paper tackled the problem of improving robustness of deep neural networks against adversarial attacks by introducing an immuno-mimetic model inspired by the immune system, resulting in up to a 12.5% improvement in adversarial accuracy on benchmark image datasets without significant loss on clean data.
Biomimetics has played a key role in the evolution of artificial neural networks. Thus far, in silico metaphors have been dominated by concepts from neuroscience and cognitive psychology. In this paper we introduce a different type of biomimetic model, one that borrows concepts from the immune system, for designing robust deep neural networks. This immuno-mimetic model leads to a new computational biology framework for robustification of deep neural networks against adversarial attacks. Within this Immuno-Net framework we define a robust adaptive immune-inspired learning system (Immuno-Net RAILS) that emulates, in silico, the adaptive biological mechanisms of B-cells that are used to defend a mammalian host against pathogenic attacks. When applied to image classification tasks on benchmark datasets, we demonstrate that Immuno-net RAILS results in improvement of as much as 12.5% in adversarial accuracy of a baseline method, the DkNN-robustified CNN, without appreciable loss of accuracy on clean data.