The Translucent Patch: A Physical and Universal Attack on Object Detectors
Physical adversarial attacks against object detectors have seen increasing success in recent years. However, these attacks require direct access to the object of interest in order to apply a physical patch. Furthermore, to hide multiple objects, an adversarial patch must be applied to each object. In this paper, we propose a contactless translucent physical patch containing a carefully constructed pattern, which is placed on the camera's lens, to fool state-of-the-art object detectors. The primary goal of our patch is to hide all instances of a selected target class. In addition, the optimization method used to construct the patch aims to ensure that the detection of other (untargeted) classes remains unharmed. Therefore, in our experiments, which are conducted on state-of-the-art object detection models used in autonomous driving, we study the effect of the patch on the detection of both the selected target class and the other classes. We show that our patch was able to prevent the detection of 42.27% of all stop sign instances while maintaining high (nearly 80%) detection of the other classes.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Attacking Object Detector Using A Universal Targeted Label-Switch Patch
Adversarial attacks against deep learning-based object detectors (ODs) have been studied extensively in the past few years. These attacks cause the model to make incorrect predictions by placing a patch containing an adv…
ObjectAdversarial camera stickers: A physical camera-based attack on deep learning systems
Recent work has documented the susceptibility of deep learning systems to adversarial examples, but most such attacks directly manipulate the digital input to a classifier. Although a smaller line of work considers physi…
When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
Vision-Language-Action (VLA) models are vulnerable to adversarial attacks, yet universal and transferable attacks remain underexplored, as most existing patches overfit to a single model and fail in black-box settings. T…
Meta Adversarial Training against Universal Patches
Recently demonstrated physical-world adversarial attacks have exposed vulnerabilities in perception systems that pose severe risks for safety-critical applications such as autonomous driving. These attacks place adversar…
Autonomous Drivingimage-classificationImage ClassificationMeta-LearningCDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors
Adversarial patches are widely used to evaluate the robustness of object detection systems in real-world scenarios. These patches were initially designed to deceive single-modal detectors (e.g., visible or infrared) and …
Data Augmentationobject-detectionObject Detection