RAILS: A Robust Adversarial Immune-inspired Learning System
Lists
Only you see this
Abstract
Adversarial attacks against deep neural networks are continuously evolving. Without effective defenses, they can lead to catastrophic failure. The long-standing and arguably most powerful natural defense system is the mammalian immune system, which has successfully defended against attacks by novel pathogens for millions of years. In this paper, we propose a new adversarial defense framework, called the Robust Adversarial Immune-inspired Learning System (RAILS). RAILS incorporates an Adaptive Immune System Emulation (AISE), which emulates in silico the biological mechanisms that are used to defend the host against attacks by pathogens. We use RAILS to harden Deep k-Nearest Neighbor (DkNN) architectures against evasion attacks. Evolutionary programming is used to simulate processes in the natural immune system: B-cell flocking, clonal expansion, and affinity maturation. We show that the RAILS learning curve exhibits similar diversity-selection learning phases as observed in our in vitro biological experiments. When applied to adversarial image classification on three different datasets, RAILS delivers an additional 5.62%/12.56%/4.74% robustness improvement as compared to applying DkNN alone, without appreciable loss of accuracy on clean data.
BibTeX
@inproceedings{wang2022rails,
author = {Ren Wang and Tianqi Chen and Stephen Lindsly and Alnawaz Rehemtulla and Alfred Hero and Indika Rajapakse},
title = {{RAILS: A Robust Adversarial Immune-inspired Learning System}},
booktitle = {IEEE Access},
year = {2022},
url = {https://openreview.net/forum?id=Ku9AzTLrEUf},
}| Immuno-mimetic Deep Neural Networks (Immuno-Net) | arXiv · 2021 |
| Modeling Biological Immunity to Adversarial Examples | CVPR · 2020 |
| Guarding Against Adversarial Attacks using Biologically Inspired Contour Integration | Journal of Computational Vision and Imaging Systems · 2018 |
| Fooling the classifier: Ligand antagonism and adversarial examples | arXiv · 2018 |
| Evolving Robust Neural Architectures to Defend from Adversarial Attacks | arXiv · 2019 |
| Towards Adversarial Robustness via Feature Matching | IEEE Access · 2020 |