SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1712.02779 · 2017

Exploring the Landscape of Spatial Robustness

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

The study of adversarial robustness has so far largely focused on perturbations bound in p-norms. However, state-of-the-art models turn out to be also vulnerable to other, more natural classes of perturbations such as translations and rotations. In this work, we thoroughly investigate the vulnerability of neural network--based classifiers to rotations and translations. While data augmentation offers relatively small robustness, we use ideas from robust optimization and test-time input aggregation to significantly improve robustness. Finally we find that, in contrast to the p-norm case, first-order methods cannot reliably find worst-case perturbations. This highlights spatial robustness as a fundamentally different setting requiring additional study. Code available at https://github.com/MadryLab/adversarial_spatial and https://github.com/MadryLab/spatial-pytorch.

For agents

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

get_harvested_code_for_paper("1712.02779")
get_code_for_paper("1712.02779")
have("1712.02779")

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

curl https://syntology.ai/api/ran/1712.02779.json

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

[![Syntology run record](https://syntology.ai/api/ran/1712.02779.svg)](https://syntology.ai/paper/1712.02779)

Connect an agent — have() is free.