Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images

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.

References in corpus (16)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Ensemble Adversarial Training: Attacks and Defenses
• Synthesizing Robust Adversarial Examples
• Anchor-free Oriented Proposal Generator for Object Detection
• Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks
• ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector
• DPatch: An Adversarial Patch Attack on Object Detectors
• On Physical Adversarial Patches for Object Detection
• Benchmarking Adversarial Patch Against Aerial Detection
• AI Security for Geoscience and Remote Sensing: Challenges and Future Trends
• Robust Adversarial Perturbation on Deep Proposal-based Models
• Object Hider: Adversarial Patch Attack Against Object Detectors
• Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detection
• DPAttack: Diffused Patch Attacks against Universal Object Detection

Cited by in corpus (1)

• AI Security for Geoscience and Remote Sensing: Challenges and Future Trends