Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection
Dehong Kong, Siyuan Liang, Wenqi Ren

TL;DR
This paper introduces the Environmental Matching Attack (EMA), a novel method for generating natural-looking adversarial patches for UAV object detection that maintain high attack success rates while blending with the environment.
Contribution
The paper presents the first approach to create environmentally matching, natural adversarial patches for UAVs using stable diffusion guidance, improving visual naturalness without sacrificing attack effectiveness.
Findings
Achieves nearly the same attack performance as baseline in digital scenarios.
Outperforms baseline in physical scenarios.
Produces more natural patches with better environmental blending.
Abstract
Object detection techniques for Unmanned Aerial Vehicles (UAVs) rely on Deep Neural Networks (DNNs), which are vulnerable to adversarial attacks. Nonetheless, adversarial patches generated by existing algorithms in the UAV domain pay very little attention to the naturalness of adversarial patches. Moreover, imposing constraints directly on adversarial patches makes it difficult to generate patches that appear natural to the human eye while ensuring a high attack success rate. We notice that patches are natural looking when their overall color is consistent with the environment. Therefore, we propose a new method named Environmental Matching Attack(EMA) to address the issue of optimizing the adversarial patch under the constraints of color. To the best of our knowledge, this paper is the first to consider natural patches in the domain of UAVs. The EMA method exploits strong prior…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods · Infrared Target Detection Methodologies · Fire Detection and Safety Systems
MethodsDiffusion
