paper-with-me

Papers

The Translucent Patch: A Physical and Universal Attack on Object Detectors

2020-12-23 · CVPR 2021 1 · Alon Zolfi, Moshe Kravchik, Yuval Elovici, Asaf Shabtai

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.

📄 PDF Abstract BibTeX arXiv:2012.12528

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingObjectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Attacking Object Detector Using A Universal Targeted Label-Switch Patch

2022-11-16 · Avishag Shapira, Ron Bitton, Dan Avraham, Alon Zolfi 외

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…

Object

Adversarial camera stickers: A physical camera-based attack on deep learning systems

2019-03-21 · Juncheng Li, Frank R. Schmidt, J. Zico Kolter

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

2025-11-26 · Hui Lu, Yi Yu, Yiming Yang, Chenyu Yi 외 arxiv

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

2021-01-27 · Jan Hendrik Metzen, Nicole Finnie, Robin Hutmacher

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-Learning

CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors

2025-04-15 · Jiahuan Long, Wen Yao, Tingsong Jiang, Chao Ma

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