Attacking Object Detector Using A Universal Targeted Label-Switch Patch

Shapira, Avishag; Bitton, Ron; Avraham, Dan; Zolfi, Alon; Elovici, Yuval; Shabtai, Asaf

doi:10.48550/arxiv.2211.08859

Cited by 4 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Shapira et al [89] developed a targeted attack method to generate the adversarial patch that is pasted on the car hood to attack object detectors (i.e., YOLOv3 and Faster RCNN) in a more realistic monitor scenario. Specifically, the author devised a tailored projection method to adaptively adjust the position and shape of the adversarial patch in terms of the camera orientation.…”

Section: Switchattackmentioning

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

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: Switchattackmentioning

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

“…Face recognition entails the detection and recognition of specific individuals based on their facial characteristics, enabling applications such as identity verification, access control, and surveillance systems. The advent of deep learning models, specifically [74] White-box TV,NPS,D2P -Static 2D Adversarial YOLO [82] White-box EOT,TV,NPS -Dynamic 2D NestedAE [76] White-box D2P, Alignment Pattern, Shape and Color control loss Dynamic 3D DPATCH [69] White-box EOT -Static 2D DPatch2 [70] White-box EOT -Static 2D LPAttack [72] White-box EOT,TV,NPS -Static 2D Translucent Patch [77] White-box Affine,NPS -Static 2D SwitchPatch [73] White-box TV -Static 2D Object Hider [71] White-box --Static 2D ScreenAttack [99] White-box TV -Static 2D Invisible Cloak [81] White-box EOT,TV -Static 3D Adversarial T-shirt [84] White-box EOT,TPS -Static 2D Invisible Cloak2 [85] White-box TPS -Static 2D LAP [87] White-box TV,NPS Static 2D NAP [86] White-box TV GAN Static 2D TC-EGA [168] White-box EOT,TPS -Static 2D SLAP [78] White-box EOT,TV -Static 2D CAMOU [97] White-box EOT -Static 2D ER attack [98] Black-box --Static 3D UPC [83] White-box EOT, TV L∞ norm Static 3D DAS [101] White-box TV Evasion loss Static 3D FCA [103] White-box TV -Static 3D CAC [104] White-box EOT -Static 3D DTA [102] White-box EOT -Static 3D Adversarial Bulbs [92] White-box EOT,TV -Static 2D QRAttack [93] White-box EOT,TPS Material Static 2D HOTCOLD [94] White-box SSP Material Static 2D AIP [95] White-box Binary & Aggregation regularization Material Static 2D AdvIB [96] Black-box EOT Material Static 2D PG [100] Black-box --Static 2D AdvART [89] White-box EOT, TV Similarity loss Static 2D DAP [91] White-box EOT, TV Similarity loss Dynamic 2D TPatch…”

Section: Physical Attacks On Face Recognition and Person Re-identific...mentioning

confidence: 99%

Physical Adversarial Attacks for Camera-Based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook

Guesmi,

Hanif,

Ouni

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) have shown impressive performance in computer vision tasks; however, their vulnerability to adversarial attacks raises concerns regarding their security and reliability. Extensive research has shown that DNNs can be compromised by carefully crafted perturbations, leading to significant performance degradation in both digital and physical domains. Therefore, ensuring the security of DNN-based systems is crucial, particularly in safety-critical domains such as autonomous driving, robotics, smart homes/cities, smart industries, video surveillance, and healthcare. In this paper, we present a comprehensive survey of the current trends focusing specifically on physical adversarial attacks. We aim to provide a thorough understanding of the concept of physical adversarial attacks, analyzing their key characteristics and distinguishing features. Furthermore, we explore the specific requirements and challenges associated with executing attacks in the physical world. Our article delves into various physical adversarial attack methods, categorized according to their target tasks in different applications, including classification, detection, face recognition, semantic segmentation and depth estimation. We assess the performance of these attack methods in terms of their effectiveness, stealthiness, and robustness. We examine how each technique strives to ensure the successful manipulation of DNNs while mitigating the risk of detection and withstanding real-world distortions. Lastly, we discuss the current challenges and outline potential future research directions in the field of physical adversarial attacks. We highlight the need for enhanced defense mechanisms, the exploration of novel attack strategies, the evaluation of attacks in different application domains, and the establishment of standardized benchmarks and evaluation criteria for physical adversarial attacks. Through this comprehensive survey, we aim to provide a valuable resource for researchers, practitioners, and policymakers to gain a holistic understanding of physical adversarial attacks in computer vision and facilitate the development of robust and secure DNN-based systems.

show abstract

“…The DAS achieves strong transferability by suppressing both model and human attention, thereby enhancing the efficacy of the attack. In [194], the researchers propose a novel targeted and universal attack against the SOTA object detector using a label-switching technique. The attack aims to fool the object detector into misclassifying a specific target object as another object category chosen by the attacker.…”

Section: Black-box Attacksmentioning

confidence: 99%

“…In paper [95], the authors conduct the first investigation towards adversarial attacks that are directed at X-ray prohibited item detection and demonstrate the grave hazards posed by such attacks in this context of paramount safety significance. Finally, we summarize physical attacks against object detection ( [65], [76], [94]- [96], [105]- [107], [160], [184]- [190], [192]- [194], [197], [201]- [204]) in Table VI.…”

Section: Black-box Attacksmentioning

confidence: 99%

Benchmarking Adversarial Patch Against Aerial Detection

Lian

Mei

Zhang

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial noises. Surprisingly, there has been a lack of comprehensive studies on the robustness of RS tasks, prompting us to undertake a thorough survey and benchmark on the robustness of image classification and object detection in RS. To our best knowledge, this study represents the first comprehensive examination of both natural robustness and adversarial robustness in RS tasks. Specifically, we have curated and made publicly available datasets that contain natural and adversarial noises. These datasets serve as valuable resources for evaluating the robustness of DNNs-based models. To provide a comprehensive assessment of model robustness, we conducted meticulous experiments with numerous different classifiers and detectors, encompassing a wide range of mainstream methods. Through rigorous evaluation, we have uncovered insightful and intriguing findings, which shed light on the relationship between adversarial noise crafting and model training, yielding a deeper understanding of the susceptibility and limitations of various models, and providing guidance for the development of more resilient and robust models

show abstract

Attacking Object Detector Using A Universal Targeted Label-Switch Patch

Cited by 4 publications

References 18 publications

A Survey on Physical Adversarial Attack in Computer Vision

A Survey on Physical Adversarial Attack in Computer Vision

Physical Adversarial Attacks for Camera-Based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook

Benchmarking Adversarial Patch Against Aerial Detection

Contact Info

Product

Resources

About