# Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches

Source: [Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches](<https://www.sota2.com/research/paper/68fa6fe21e209131cea47e83>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:59.722Z

Authors: Aniruddha Saha, Shuhua Yu, Arash Norouzzadeh, Wan-Yi Lin, Chaithanya Kumar Mummadi

Published: 2023-06-22T00:13:44.000Z

## Abstract

Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser arXiv:2108.09135 \[cs.CV\], the state-of-the-art certified defense, uses a double-masking strategy for robust classification. The success of this strategy relies heavily on the model's invariance to image pixel masking. In this paper, we take a closer look at model training schemes to improve this invariance. Instead of using Random Cutout arXiv:1708.04552v2 \[cs.CV\] augmentations like PatchCleanser, we introduce the notion of worst-case masking, i.e., selecting masked images which maximize classification loss. However, finding worst-case masks requires an exhaustive search, which might be prohibitively expensive to do on-the-fly during training. To solve this problem, we propose a two-round greedy masking strategy (Greedy Cutout) which finds an approximate worst-case mask location with much less compute. We show that the models trained with our Greedy Cutout improves certified robust accuracy over Random Cutout in PatchCleanser across a range of datasets and architectures. Certified robust accuracy on ImageNet with a ViT-B16-224 model increases from 58.1\\% to 62.3\\% against a 3\\% square patch applied anywhere on the image.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.12610>)

[PDF](<https://arxiv.org/pdf/2306.12610.pdf>)
