# Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks

arXiv: https://arxiv.org/abs/2510.04245 · HTML: https://mlsanity.com/paper/2510.04245/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 18 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [CRAFT: Concept Recursive Activation FacTorization for Explainability](https://mlsanity.com/paper/2211.10154/) (2022)
- [SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems](https://mlsanity.com/paper/1812.00292/) (2018)
- [LaVAN: Localized and Visible Adversarial Noise](https://mlsanity.com/paper/1801.02608/) (2018)
- [Certified Defenses for Adversarial Patches](https://mlsanity.com/paper/2003.06693/) (2020)
- [Local Gradients Smoothing: Defense against localized adversarial attacks](https://mlsanity.com/paper/1807.01216/) (2018)
- [Interpretable Deep Learning under Fire](https://mlsanity.com/paper/1812.00891/) (2018)
- [PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier](https://mlsanity.com/paper/2108.09135/) (2021)
- [ML-LOO: Detecting Adversarial Examples with Feature Attribution](https://mlsanity.com/paper/1906.03499/) (2019)
- [Minority Reports Defense: Defending Against Adversarial Patches](https://mlsanity.com/paper/2004.13799/) (2020)
- [PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch](https://mlsanity.com/paper/2207.01795/) (2022)
- [Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks](https://mlsanity.com/paper/2108.05075/) (2021)
- [SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability](https://mlsanity.com/paper/2210.17376/) (2022)
- [Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense](https://mlsanity.com/paper/2304.06919/) (2023)
- [PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis](https://mlsanity.com/paper/2404.10789/) (2024)

## Built on by (most cited first, 1 of 1)

- [Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?](https://mlsanity.com/paper/2609.08331/) (2026)

## Abstract (arXiv)

Adversarial patch attacks pose a practical threat to deep learning models by forcing targeted misclassifications through localized perturbations, often realized in the physical world. Existing defenses typically assume prior knowledge of patch size or location, limiting their applicability. In this work, we propose a patch-agnostic defense that leverages concept-based explanations to identify and suppress the most influential concept activation vectors, thereby neutralizing patch effects without explicit detection. Evaluated on Imagenette with a ResNet-50, our method achieves higher robust and clean accuracy than the state-of-the-art PatchCleanser, while maintaining strong performance across varying patch sizes and locations. Our results highlight the promise of combining interpretability with robustness and suggest concept-driven defenses as a scalable strategy for securing machine learning models against adversarial patch attacks.