ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches

Maura Pintor, Daniele Angioni, Angelo Sotgiu, Luca Demetrio, Ambra Demontis, Battista Biggio, Fabio Roli

Keywords: adversarial machine learning, machine learning, out of ditribution detection, computer vision

TL;DR: A dataset for benchmarking machine learning robustness against adversarial patches, based on the ImageNet dataset and adversarial patch attacks.

Abstract:

Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it.
However, their optimization is computationally demanding and requires careful hyperparameter tuning.
To overcome these issues, we propose ImageNet-Patch, a dataset to benchmark machine-learning models against adversarial patches.
It consists of a set of patches optimized to generalize across different models and applied to ImageNet data after preprocessing them with affine transformations.
This process enables an approximate yet faster robustness evaluation, leveraging the transferability of adversarial perturbations.

Track: Full submission

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2203.04412/code)