SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.13370 · 2020

Towards Deep Learning Models Resistant to Large Perturbations

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Adversarial robustness has proven to be a required property of machine learning algorithms. A key and often overlooked aspect of this problem is to try to make the adversarial noise magnitude as large as possible to enhance the benefits of the model robustness. We show that the well-established algorithm called "adversarial training" fails to train a deep neural network given a large, but reasonable, perturbation magnitude. In this paper, we propose a simple yet effective initialization of the network weights that makes learning on higher levels of noise possible. We next evaluate this idea rigorously on MNIST ($ε$ up to $\approx 0.40$) and CIFAR10 ($ε$ up to $\approx 32/255$) datasets assuming the $\ell_{\infty}$ attack model. Additionally, in order to establish the limits of $ε$ in which the learning is feasible, we study the optimal robust classifier assuming full access to the joint data and label distribution. Then, we provide some theoretical results on the adversarial accuracy for a simple multi-dimensional Bernoulli distribution, which yields some insights on the range of feasible perturbations for the MNIST dataset.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.13370")
get_code_for_paper("2003.13370")
have("2003.13370")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2003.13370.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2003.13370.svg)](https://syntology.ai/paper/2003.13370)

Connect an agent — have() is free.