Immuno-mimetic Deep Neural Networks (Immuno-Net)

TL;DR

This paper introduces Immuno-Net, a biomimetic deep neural network inspired by the immune system, which enhances robustness against adversarial attacks while maintaining accuracy on clean data.

Contribution

It proposes a novel immune-inspired framework for deep neural network robustness, specifically through the Immuno-Net RAILS system, inspired by biological B-cell mechanisms.

Findings

Up to 12.5% improvement in adversarial accuracy

Maintains accuracy on clean data

Demonstrates effectiveness on benchmark datasets

Abstract

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.