Significant work is being done to develop the math and tools necessary to build provable defenses, or at least bounds, against adversarial attacks of neural networks. In this work, we argue that tools from control theory could be leveraged to aid in defending against such attacks. We do this by example, building a provable defense against a weaker adversary. This is done so we can focus on the mechanisms of control theory, and illuminate its intrinsic value.
@article{arxiv.1907.07732,
title = {Connecting Lyapunov Control Theory to Adversarial Attacks},
author = {Arash Rahnama and Andre T. Nguyen and Edward Raff},
journal= {arXiv preprint arXiv:1907.07732},
year = {2019}
}
Comments
8 pages, 3 figures, AdvML'19: Workshop on Adversarial Learning Methods for Machine Learning and Data Mining at KDD