# PatchBlock: A Lightweight Defense Against Adversarial Patches for Embedded EdgeAI Devices

arXiv: https://arxiv.org/abs/2601.00367 · HTML: https://mlsanity.com/paper/2601.00367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 1 Jan 2026.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [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)
- [(De)Randomized Smoothing for Certifiable Defense against Patch Attacks](https://mlsanity.com/paper/2002.10733/) (2020)
- [Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training](https://mlsanity.com/paper/1907.10764/) (2019)
- [Local Gradients Smoothing: Defense against localized adversarial attacks](https://mlsanity.com/paper/1807.01216/) (2018)
- [Extended Isolation Forest](https://mlsanity.com/paper/1811.02141/) (2018)
- [Deep Defense: Training DNNs with Improved Adversarial Robustness](https://mlsanity.com/paper/1803.00404/) (2018)
- [DAP: A Dynamic Adversarial Patch for Evading Person Detectors](https://mlsanity.com/paper/2305.11618/) (2023)
- [Jedi: Entropy-based Localization and Removal of Adversarial Patches](https://mlsanity.com/paper/2304.10029/) (2023)
- [PAD: Patch-Agnostic Defense against Adversarial Patch Attacks](https://mlsanity.com/paper/2404.16452/) (2024)
- [Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook](https://mlsanity.com/paper/2308.06173/) (2023)
- [Generative Dynamic Patch Attack](https://mlsanity.com/paper/2111.04266/) (2021)
- [Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks](https://mlsanity.com/paper/2108.05075/) (2021)
- [AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systems](https://mlsanity.com/paper/2303.01338/) (2023)
- [ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches](https://mlsanity.com/paper/2311.12084/) (2023)
- [Anomaly Unveiled: Securing Image Classification against Adversarial Patch Attacks](https://mlsanity.com/paper/2402.06249/) (2024)
- [SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications](https://mlsanity.com/paper/2403.11515/) (2024)

## Abstract (arXiv)

Adversarial attacks pose a significant challenge to the reliable deployment of machine learning models in EdgeAI applications, such as autonomous driving and surveillance, which rely on resource-constrained devices for real-time inference. Among these, patch-based adversarial attacks, where small malicious patches (e.g., stickers) are applied to objects, can deceive neural networks into making incorrect predictions with potentially severe consequences. In this paper, we present PatchBlock, a lightweight framework designed to detect and neutralize adversarial patches in images. Leveraging outlier detection and dimensionality reduction, PatchBlock identifies regions affected by adversarial noise and suppresses their impact. It operates as a pre-processing module at the sensor level, efficiently running on CPUs in parallel with GPU inference, thus preserving system throughput while avoiding additional GPU overhead. The framework follows a three-stage pipeline: splitting the input into chunks (Chunking), detecting anomalous regions via a redesigned isolation forest with targeted cuts for faster convergence (Separating), and applying dimensionality reduction on the identified outliers (Mitigating). PatchBlock is both model- and patch-agnostic, can be retrofitted to existing pipelines, and integrates seamlessly between sensor inputs and downstream models. Evaluations across multiple neural architectures, benchmark datasets, attack types, and diverse edge devices demonstrate that PatchBlock consistently improves robustness, recovering up to 77% of model accuracy under strong patch attacks such as the Google Adversarial Patch, while maintaining high portability and minimal clean accuracy loss. Additionally, PatchBlock outperforms the state-of-the-art defenses in efficiency, in terms of computation time and energy consumption per sample, making it suitable for EdgeAI applications.