# Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks

arXiv: https://arxiv.org/abs/2403.12988 · HTML: https://mlsanity.com/paper/2403.12988/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 4 Mar 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 12 of 12)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Eigen-CAM: Class Activation Map using Principal Components](https://mlsanity.com/paper/2008.00299/) (2020)
- [Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection](https://mlsanity.com/paper/2112.04532/) (2021)
- [Physical Adversarial Attack meets Computer Vision: A Decade Survey](https://mlsanity.com/paper/2209.15179/) (2022)
- [Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector](https://mlsanity.com/paper/2307.08076/) (2023)
- [Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectors](https://mlsanity.com/paper/2303.04238/) (2023)
- [MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World](https://mlsanity.com/paper/2312.17431/) (2023)
- [Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizer](https://mlsanity.com/paper/2303.10291/) (2023)
- [Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patches](https://mlsanity.com/paper/2305.10929/) (2023)

## Built on by (most cited first, 2 of 2)

- [Seeing Isn't Believing: Context-Aware Adversarial Patch Synthesis via Conditional GAN](https://mlsanity.com/paper/2509.22836/) (2025)
- [Learning What to Fail On: Failure-Mode Contextual Bandits for Adversarial Data Curation](https://mlsanity.com/paper/2608.18681/) (2026)

## Abstract (arXiv)

The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against such attacks. Optimized adversarial patches were generated and placed in sensitive image regions, by applying EigenCAM and grid search to determine optimal placement. We tested several defenses, including Segment and Complete (SAC), Inpainting, and Latent Diffusion Models. Our pipeline comprises three main stages: patch application, object detection, and defense analysis. Results indicate that adversarial patches reduce average detection confidence by 22.06%. Defenses restored confidence levels by 3.45% (SAC), 5.05% (Inpainting), and significantly improved them by 26.61%, which even exceeds the original accuracy levels, when using the Latent Diffusion Model, highlighting its superior effectiveness in mitigating the effects of adversarial patches.