# The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches

arXiv: https://arxiv.org/abs/2604.26317 · HTML: https://mlsanity.com/paper/2604.26317/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 72 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Fooling automated surveillance cameras: adversarial patches to attack person detection](https://mlsanity.com/paper/1904.08653/) (2019)
- [LaVAN: Localized and Visible Adversarial Noise](https://mlsanity.com/paper/1801.02608/) (2018)
- [On Physical Adversarial Patches for Object Detection](https://mlsanity.com/paper/1906.11897/) (2019)
- [Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots](https://mlsanity.com/paper/2203.06967/) (2022)
- [Adversarial camera stickers: A physical camera-based attack on deep learning systems](https://mlsanity.com/paper/1904.00759/) (2019)
- [Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection](https://mlsanity.com/paper/2112.04532/) (2021)
- [The Translucent Patch: A Physical and Universal Attack on Object Detectors](https://mlsanity.com/paper/2012.12528/) (2020)
- [Certified Patch Robustness via Smoothed Vision Transformers](https://mlsanity.com/paper/2110.07719/) (2021)
- [IDR: Self-Supervised Image Denoising via Iterative Data Refinement](https://mlsanity.com/paper/2111.14358/) (2021)
- [Jedi: Entropy-based Localization and Removal of Adversarial Patches](https://mlsanity.com/paper/2304.10029/) (2023)
- [Detection based Defense against Adversarial Examples from the Steganalysis Point of View](https://mlsanity.com/paper/1806.09186/) (2018)
- [Downstream-agnostic Adversarial Examples](https://mlsanity.com/paper/2307.12280/) (2023)
- [PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch](https://mlsanity.com/paper/2207.01795/) (2022)
- [ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches](https://mlsanity.com/paper/2203.04412/) (2022)
- [DPAttack: Diffused Patch Attacks against Universal Object Detection](https://mlsanity.com/paper/2010.11679/) (2020)
- [RPATTACK: Refined Patch Attack on General Object Detectors](https://mlsanity.com/paper/2103.12469/) (2021)
- [Self-Supervised Image Restoration with Blurry and Noisy Pairs](https://mlsanity.com/paper/2211.07317/) (2022)
- [Adversarial Patch Camouflage against Aerial Detection](https://mlsanity.com/paper/2008.13671/) (2020)
- [DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks](https://mlsanity.com/paper/2306.09124/) (2023)
- [Vax-a-Net: Training-time Defence Against Adversarial Patch Attacks](https://mlsanity.com/paper/2009.08194/) (2020)
- [Patch Attack Invariance: How Sensitive are Patch Attacks to 3D Pose?](https://mlsanity.com/paper/2108.07229/) (2021)
- [Robustness Out of the Box: Compositional Representations Naturally Defend Against Black-Box Patch Attacks](https://mlsanity.com/paper/2012.00558/) (2020)

## Abstract (arXiv)

The vulnerabilities of deep neural networks against singularities have raised serious concerns regarding their deployment in the physical world. One of the most prominent and impactful physical-world adversarial perturbations is the attachment of patches to clean images, known as an adversarial patch attack. Similarly, natural noises such as Gaussian and Salt&Pepper are highly prevalent in the real world. The current research need arises from the above vulnerabilities and the lack of efforts to tackle these two singularities independently and, especially, in combination. In this research, we have, for the first time, combined these two prominent singularities and proposed a novel dataset. Using this dataset, we have conducted a benchmark study of singularity data-point detection using features from several convolutional neural networks. For classification, rather than the popular neural network-based parameter tuning, we have used traditional yet effective machine learning classifiers. The extensive experiments across various in- and out-of-distribution (OOD) singularities reveal several interesting findings about the effectiveness of classifiers and show that it is hard to defend against adversaries when they are treated independently, and inefficient classifiers are selected.