Compositional Curvature Bounds for Deep Neural Networks
Abstract
A key challenge that threatens the widespread use of neural networks in safety-critical applications is their vulnerability to adversarial attacks. In this paper, we study the second-order behavior of continuously differentiable deep neural networks, focusing on robustness against adversarial perturbations. First, we provide a theoretical analysis of robustness and attack certificates for deep classifiers by leveraging local gradients and upper bounds on the second derivative (curvature constant). Next, we introduce a novel algorithm to analytically compute provable upper bounds on the second derivative of neural networks. This algorithm leverages the compositional structure of the model to propagate the curvature bound layer-by-layer, giving rise to a scalable and modular approach. The proposed bound can serve as a differentiable regularizer to control the curvature of neural networks during training, thereby enhancing robustness. Finally, we demonstrate the efficacy of our method on classification tasks using the MNIST and CIFAR-10 datasets.
Cite
@article{arxiv.2406.05119,
title = {Compositional Curvature Bounds for Deep Neural Networks},
author = {Taha Entesari and Sina Sharifi and Mahyar Fazlyab},
journal= {arXiv preprint arXiv:2406.05119},
year = {2024}
}
Comments
Proceedings of the 41 st International Conference on Machine Learning (ICML 2024)