🤖 AI Summary
To address the vulnerability of object detectors to adversarial patch attacks in UAV aerial imaging, this paper proposes a model-agnostic defense method that formulates adversarial patch removal as an unsupervised occlusion restoration task—requiring no ground-truth adversarial samples, no target-model dependency, and zero-shot deployment. The core contribution is the first reformulation of adversarial defense as a structure-guided image inpainting problem, enabled by a lightweight, single-stage neural network that jointly enforces texture consistency and geometric structural priors. Evaluated under both digital simulation and physical-world UAV experiments, the method reduces attack success rates by ≥82% on average while preserving detection accuracy (mAP degradation <1.2%) and incurring minimal inference latency (<15 ms). Its plug-and-play design allows seamless integration into existing UAV-based detection pipelines without architectural or training modifications.
📝 Abstract
Object detection forms a key component in Unmanned Aerial Vehicles (UAVs) for completing high-level tasks that depend on the awareness of objects on the ground from an aerial perspective. In that scenario, adversarial patch attacks on an onboard object detector can severely impair the performance of upstream tasks. This paper proposes a novel model-agnostic defense mechanism against the threat of adversarial patch attacks in the context of UAV-based object detection. We formulate adversarial patch defense as an occlusion removal task. The proposed defense method can neutralize adversarial patches located on objects of interest, without exposure to adversarial patches during training. Our lightweight single-stage defense approach allows us to maintain a model-agnostic nature, that once deployed does not require to be updated in response to changes in the object detection pipeline. The evaluations in digital and physical domains show the feasibility of our method for deployment in UAV object detection pipelines, by significantly decreasing the Attack Success Ratio without incurring significant processing costs. As a result, the proposed defense solution can improve the reliability of object detection for UAVs.