Adversarial Patch Attack on Multi-Scale Object Detection for UAV Remote Sensing Images

Zhang, Yichuang; Zhang, Yu; Qi, Jiahao; Bin, Kangcheng; Wen, Hao; Tong, Xunqian; Zhong, Ping

doi:10.3390/rs14215298

Cited by 32 publications

(12 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concurrent to [101], Zhang et al [131] focused on crafted adversarial patch attack against the object detection in the scenario of multi-scale objects of remote sensing. Specifically, the author first collected numerous aerial images by a drone, then optimized the adversarial patch under a set of transformations with the devised loss function, composed of the YOLO's training loss, TV loss, and NPS loss.…”

Section: Type Onmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Physical Adversarial Attack in Computer Vision

Wang¹,

Wen²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

In the past decade, deep learning has dramatically changed the traditional hand-craft feature manner with strong feature learning capability, promoting the tremendous improvement of conventional tasks. However, deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples crafted by small noise, which is imperceptible to human observers but can make DNNs misbehave. Existing adversarial attacks can be divided into digital and physical adversarial attacks. The former is designed to pursue strong attack performance in lab environments while hardly remaining effective when applied to the physical world. In contrast, the latter focus on developing physical deployable attacks, which are more robust in complex physical environmental conditions (e.g., brightness, occlusion, etc.). Recently, with the increasing deployment of the DNN-based system in the real world, enhancing the robustness of these systems is an emergency, while exploring physical adversarial attacks exhaustly is the precondition. To this end, this paper reviews the development of physical adversarial attacks against DNN-based computer vision tasks (i.e., image recognition and object detection tasks), which can provide beneficial information for developing stronger physical adversarial attacks. For completeness, we also briefly introduce the works that do not involve physical attacks but are closely related to them. Specifically, we first proposed a taxonomy to summarize the current physical adversarial attacks. Then we briefly discuss the existing physical attacks and focus on the technique for improving the robustness of physical attacks under complex physical environmental conditions. Finally, we discuss the issues of the current physical adversarial attacks to be solved and give promising directions.

show abstract

Section: Type Onmentioning

confidence: 99%

“…Figure 18 illustrates the captured physical adversarial examples. [131] [132] Apart from two adversarial patch attacks against the object detector on the aerial imagery dataset, there are a number of attempts to attack the remote sensing image recognition, and detection [133][134][135].…”

Section: Type Onmentioning

confidence: 99%

A Survey on Physical Adversarial Attack in Computer Vision

Wang¹,

Wen²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Consequently, Delving into adversarial attacks against aerial detection paves a critical path to better explaining and improving model robustness. However, most adversarial attack methods [17], [19], [45]- [47] against aerial detection concentrate on the digital domain. In contrast, physical attacks against aerial detection are somewhat scarce, while it is more critical and practical.…”

Section: B Physical Attackmentioning

confidence: 99%

CBA: Contextual Background Attack against Optical Aerial Detection in the Physical World

Lian¹,

Wang²,

Su³

et al. 2023

Preprint

View full text Add to dashboard Cite

Patch-based physical attacks have increasingly aroused concerns. However, most existing methods focus on obscuring targets captured on the ground, and some of these methods are simply extended to deceive aerial detectors. They smear the targeted objects in the physical world with the elaborated adversarial patches, which can only slightly sway the aerial detectors' prediction and with weak attack transferability. To address the above issues, we propose to perform Contextual Background Attack (CBA), a novel physical attack framework against aerial detection, which can achieve strong attack efficacy and transferability in the physical world even without smudging the interested objects at all. Specifically, the targets of interest, i.e. the aircraft in aerial images, are adopted to mask adversarial patches. The pixels outside the mask area are optimized to make the generated adversarial patches closely cover the critical contextual background area for detection, which contributes to gifting adversarial patches with more robust and transferable attack potency in the real world. To further strengthen the attack performance, the adversarial patches are forced to be outside targets during training, by which the detected objects of interest, both on and outside patches, benefit the accumulation of attack efficacy. Consequently, the sophisticatedly designed patches are gifted with solid fooling efficacy against objects both on and outside the adversarial patches simultaneously. Extensive proportionally scaled experiments are performed in physical scenarios, demonstrating the superiority and potential of the proposed framework for physical attacks. We expect that the proposed physical attack method will serve as a benchmark for assessing the adversarial robustness of diverse aerial detectors and defense methods. The code has been released at https://github.com/JiaweiLian/CBA.

show abstract

“…Ref. [44] evaluated the attack ability on different scales objects, they also perform physical adversarial attacks on multi-scale objects. Rust-Style Patch [45] works on improving the natural and robust adversarial patches by utilizing style transfer on remote sensing, and the authors conducted experiments in both the digital and physical domains.…”

Section: Adversarial Attacks In Remote Sensingmentioning

confidence: 99%

Attention-Enhanced One-Shot Attack against Single Object Tracking for Unmanned Aerial Vehicle Remote Sensing Images

Jiang,

Yin

2023

Remote Sensing

View full text Add to dashboard Cite

Recent studies have shown that deep-learning-based models for processing Unmanned Aerial Vehicle (UAV) remote sensing images are vulnerable to artificially designed adversarial examples, which can lead to incorrect predictions of deep models when facing adversarial examples. Previous adversarial attack methods have mainly focused on the classification and detection of UAV remote sensing images, and there is still a lack of research on adversarial attacks for object tracking in UAV video. To address this challenge, we propose an attention-enhanced one-shot adversarial attack method for UAV remote sensing object tracking, which perturbs only the template frame and generates adversarial samples offline. First, we employ an attention feature loss to make the original frame’s features dissimilar to those of the adversarial frame, and an attention confidence loss to either suppress or enhance different confidence scores. Additionally, by forcing the tracker to concentrate on the background information near the target, a background distraction loss is used to mismatch templates with subsequent frames. Finally, we add total variation loss to generate adversarial examples that appear natural to humans. We validate the effectiveness of our method against popular trackers such as SiamRPN, DaSiamRPN, and SiamRPN++ on the UAV123 remote sensing dataset. Experimental results verify the superior attack performance of our proposed method.

show abstract

Adversarial Patch Attack on Multi-Scale Object Detection for UAV Remote Sensing Images

Cited by 32 publications

References 37 publications

A Survey on Physical Adversarial Attack in Computer Vision

A Survey on Physical Adversarial Attack in Computer Vision

CBA: Contextual Background Attack against Optical Aerial Detection in the Physical World

Attention-Enhanced One-Shot Attack against Single Object Tracking for Unmanned Aerial Vehicle Remote Sensing Images

Contact Info

Product

Resources

About