Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images

TL;DR

This paper introduces a novel Threatening Patch Attack (TPA) method on object detection in Optical Remote Sensing Images, demonstrating its effectiveness across multiple detectors and benchmarks without compromising visual quality.

Contribution

It proposes a new TPA method using FOD for patch selection and BDL for loss, addressing local-global landscape inconsistency and gradient inundation issues in remote sensing images.

Findings

TPA significantly degrades detection performance on DIOR and DOTA datasets.

Effective across four different object detectors.

First study of patch attacks on remote sensing object detection.

Abstract

Advanced Patch Attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks. However, little attention has been paid to this topic in Optical Remote Sensing Images (O-RSIs). To this end, we focus on this research, i.e., PAs on object detection in O-RSIs, and propose a more Threatening PA without the scarification of the visual quality, dubbed TPA. Specifically, to address the problem of inconsistency between local and global landscapes in existing patch selection schemes, we propose leveraging the First-Order Difference (FOD) of the objective function before and after masking to select the sub-patches to be attacked. Further, considering the problem of gradient inundation when applying existing coordinate-based loss to PAs directly, we design an IoU-based objective function specific for PAs, dubbed Bounding box Drifting Loss (BDL), which pushes the detected bounding boxes far from the initial ones until there are no intersections between them. Finally, on two widely used benchmarks, i.e., DIOR and DOTA, comprehensive evaluations of our TPA with four typical detectors (Faster R-CNN, FCOS, RetinaNet, and YOLO-v4) witness its remarkable effectiveness. To the best of our knowledge, this is the first attempt to study the PAs on object detection in O-RSIs, and we hope this work can get our readers interested in studying this topic.