# Robustness Out of the Box: Compositional Representations Naturally Defend Against Black-Box Patch Attacks

arXiv: https://arxiv.org/abs/2012.00558 · HTML: https://mlsanity.com/paper/2012.00558/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 4 of 4)

- [PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier](https://mlsanity.com/paper/2108.09135/) (2021)
- [Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey](https://mlsanity.com/paper/2206.08304/) (2022)
- [PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses](https://mlsanity.com/paper/2310.13076/) (2023)
- [The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches](https://mlsanity.com/paper/2604.26317/) (2026)

## Abstract (arXiv)

Patch-based adversarial attacks introduce a perceptible but localized change to the input that induces misclassification. While progress has been made in defending against imperceptible attacks, it remains unclear how patch-based attacks can be resisted. In this work, we study two different approaches for defending against black-box patch attacks. First, we show that adversarial training, which is successful against imperceptible attacks, has limited effectiveness against state-of-the-art location-optimized patch attacks. Second, we find that compositional deep networks, which have part-based representations that lead to innate robustness to natural occlusion, are robust to patch attacks on PASCAL3D+ and the German Traffic Sign Recognition Benchmark, without adversarial training. Moreover, the robustness of compositional models outperforms that of adversarially trained standard models by a large margin. However, on GTSRB, we observe that they have problems discriminating between similar traffic signs with fine-grained differences. We overcome this limitation by introducing part-based finetuning, which improves fine-grained recognition. By leveraging compositional representations, this is the first work that defends against black-box patch attacks without expensive adversarial training. This defense is more robust than adversarial training and more interpretable because it can locate and ignore adversarial patches.