Digital-to-Physical Transfer of Adversarial Patches for Aerial Vehicle Detection
Quick Take
This study evaluates the effectiveness of physical adversarial patches against a YOLOv3 aerial vehicle detector, revealing that while the OFF patch achieves an 85.51% Average Objectness Reduction Rate digitally, the ON patch is more robust in real-world scenarios with an Objectness Score Ratio between 0.197 and 0.343. Weather-based augmentation does not enhance patch optimization.
Key Points
- Adversarial patches optimized digitally for aerial vehicle detection showed significant vulnerabilities.
- The OFF patch achieved an 85.51% Average Objectness Reduction Rate in digital tests.
- The ON patch demonstrated better robustness in physical environments with an OSR of 0.197-0.343.
- Non-printability and total variation constraints were used to ensure patch effectiveness.
- Weather-based augmentation did not improve the optimization of adversarial patches.
Article Content
From source RSS / original summaryarXiv:2606. 00159v1 Announce Type: new Abstract: Deep neural network (DNN)-based object detectors are widely used for analyzing aerial and satellite imagery in applications such as environmental monitoring and urban analytics. Despite their strong performance, these models are known to be vulnerable to adversarial examples, and physical adversarial attacks using printable patterns pose realistic security threats.
In this paper, we evaluate physical adversarial patch attacks against an aerial vehicle detector by bridging digital optimization and real-world deployment. Adversarial patches are optimized in the digital domain using a loss function that minimizes the maximum objectness score while incorporating non-printability score (NPS) and total variation (TV) constraints to ensure both printability and spatial smoothness. The optimized patches are printed and deployed in three configurations: ON, OFF, and OFF-Side.
Experiments using a YOLOv3 detector show that while the OFF patch achieves the highest effectiveness in the digital domain (85. 51% Average Objectness Reduction Rate (AORR)), the ON patch demonstrates superior robustness in physical environments (0. 197-0. 343 Objectness Score Ratio (OSR)) due to its consistent visibility. Furthermore, our results indicate that weather-based augmentation does not necessarily improve patch optimization in this domain.
These findings provide critical insights into the practical vulnerabilities of aerial object detection systems.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, enabling efficient fine-tuning with only 0.11% parameter updates. It significantly enhances performance in few-shot learning and domain shifts across 15 biomedical imaging datasets, demonstrating robustness for clinical applications.
