Immuno-mimetic Deep Neural Networks (Immuno-Net)
arXiv:2107.02842
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.
References in corpus (10)
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- Theoretical Models of Learning to Learn
- Recent Trends in Deep Learning Based Natural Language Processing
- Certified Adversarial Robustness via Randomized Smoothing
- Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
- Detecting Adversarial Samples from Artifacts
- On the (Statistical) Detection of Adversarial Examples
- Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
- On Detecting Adversarial Perturbations
- Adversarial Examples that Fool both Computer Vision and Time-Limited Humans