Results 21 to 30 of about 26,718 (222)
Using Frequency Attention to Make Adversarial Patch Powerful Against Person Detector
IEEE Access, 2023 Deep neural networks (DNNs) are vulnerable to adversarial attacks. In particular, object detectors may be attacked by applying a particular adversarial patch to the image.
Xiaochun Lei +5 more
doaj +1 more source
Generative Adversarial Networks for Synthesizing InSAR Patches [PDF]
CoRR, 2020 accepted in preliminary version for EUSAR2020 ...
Sibler, Philipp +4 more
openaire +3 more sources
CoRR, 2017 We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class.
Tom B. Brown +4 more
openaire +2 more sources
ShuffleDetect: Detecting Adversarial Images against Convolutional Neural Networks
Applied Sciences, 2023 Recently, convolutional neural networks (CNNs) have become the main drivers in many image recognition applications. However, they are vulnerable to adversarial attacks, which can lead to disastrous consequences.
Raluca Chitic +2 more
doaj +1 more source
Brightness-Restricted Adversarial Attack Patch
CoRR, 2023 Adversarial attack patches have gained increasing attention due to their practical applicability in physical-world scenarios. However, the bright colors used in attack patches represent a significant drawback, as they can be easily identified by human observers.
openaire +2 more sources
Eigenpatches—Adversarial Patches from Principal Components
, 2023 Adversarial patches are still a simple yet powerful white box attack that can be used to fool object detectors by suppressing possible detections. The patches of these so-called evasion attacks are computational expensive to produce and require full access to the attacked detector.
Jens Bayer +3 more
openaire +2 more sources
Harnessing Perceptual Adversarial Patches for Crowd Counting
Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022 Crowd counting, which has been widely adopted for estimating the number of people in safety-critical scenes, is shown to be vulnerable to adversarial examples in the physical world (e.g., adversarial patches). Though harmful, adversarial examples are also valuable for evaluating and better understanding model robustness.
Shunchang Liu +6 more
openaire +2 more sources
On Physical Adversarial Patches for Object Detection
CoRR, 2019 In this paper, we demonstrate a physical adversarial patch attack against object detectors, notably the YOLOv3 detector. Unlike previous work on physical object detection attacks, which required the patch to overlap with the objects being misclassified or avoiding detection, we show that a properly designed patch can suppress virtually all the detected
Mark Lee, J. Zico Kolter
openaire +2 more sources
Adversarial patch defense algorithm based on PatchTracker
网络与信息安全学报The application of deep neural networks in target detection has been widely adopted in various fields.However, the introduction of adversarial patch attacks, which add local perturbations to images to mislead deep neural networks, poses a significant ...
Zhenjie XIAO, Shiyu HUANG, Feng YE, Liqing HUANG, Tianqiang HUANG
doaj +3 more sources
Benchmarking Adversarial Patch Against Aerial Detection
IEEE Transactions on Geoscience and Remote Sensing, 2022 DNNs are vulnerable to adversarial examples, which poses great security concerns for security-critical systems. In this paper, a novel adaptive-patch-based physical attack (AP-PA) framework is proposed, which aims to generate adversarial patches that are adaptive in both physical dynamics and varying scales, and by which the particular targets can be ...
Jiawei Lian +3 more
openaire +2 more sources