Results 41 to 50 of about 5,574 (249)

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, Jiakai Wang, Aishan Liu, Yingwei Li 0002, Yijie Gao, Xianglong Liu 0001, Dacheng Tao   +6 more
openaire   +2 more sources

Adversarial example defense algorithm for MNIST based on image reconstruction

网络与信息安全学报, 2022
With the popularization of deep learning, more and more attention has been paid to its security issues.The adversarial sample is to add a small disturbance to the original image, which can cause the deep learning model to misclassify the image, which ...
Zhongyuan QIN, Zhaoxiang HE, Tao LI, Liquan CHEN   +3 more
doaj   +3 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 Halftone QR Code

IEEE Access
Recent studies have shown that machine-learning models are vulnerable to adversarial attacks. Adversarial attacks are deliberate attempts to modify the input data of a machine learning model in a way that causes it to produce incorrect predictions.
Palakorn Kamnounsing, Karin Sumongkayothin, Prarinya Siritanawan, Kazunori Kotani   +3 more
doaj   +1 more source

Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches

Sensors, 2021
Deep neural networks (DNNs), especially those used in computer vision, are highly vulnerable to adversarial attacks, such as adversarial perturbations and adversarial patches. Adversarial patches, often considered more appropriate for a real-world attack,
Yongsu Kim, Hyoeun Kang, Naufal Suryanto, Harashta Tatimma Larasati, Afifatul Mukaroh, Howon Kim   +5 more
doaj   +1 more source

Distributional Modeling for Location-Aware Adversarial Patches

CoRR, 2023
Adversarial patch is one of the important forms of performing adversarial attacks in the physical world. To improve the naturalness and aggressiveness of existing adversarial patches, location-aware patches are proposed, where the patch's location on the target object is integrated into the optimization process to perform attacks.
Xingxing Wei 0001, Shouwei Ruan, Yinpeng Dong, Hang Su 0006   +3 more
openaire   +2 more sources

Traversing the subspace of adversarial patches

Machine Vision and Applications
Abstract Despite ongoing research on the topic of adversarial examples in deep learning for computer vision, some fundamentals of the nature of these attacks remain unclear. As the manifold hypothesis posits, high-dimensional data tends to be part of a low-dimensional manifold.
Jens Bayer, Stefan Becker, David Münch, Michael Arens, Jürgen Beyerer   +4 more
openaire   +3 more sources

Transferable adversarial masked self-distillation for unsupervised domain adaptation

Complex & Intelligent Systems, 2023
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to a related unlabeled target domain. Most existing works focus on minimizing the domain discrepancy to learn global domain-invariant representation using CNN ...
Yuelong Xia, Li-Jun Yun, Chengfu Yang
doaj   +1 more source

Inverse Design of Amorphous Materials With Targeted Properties

Advanced Materials, EarlyView.
AMDEN is a diffusion model framework for the inverse design of amorphous materials with targeted properties. By incorporating Hamiltonian Monte Carlo refinement into the denoising process, the framework overcomes the challenge of generating thermally relaxed disordered structures.
Jonas A. Finkler, Yan Lin, Tao Du, Jilin Hu, Morten M. Smedskjaer   +4 more
wiley   +1 more source

Double adversarial attack against license plate recognition system

网络与信息安全学报, 2023
Recent studies have revealed that deep neural networks (DNN) used in artificial intelligence systems are highly vulnerable to adversarial sample-based attacks.To address this issue, a dual adversarial attack method was proposed for license plate ...
Xianyi CHEN, Jun GU, Kai YAN, Dong JIANG, Linfeng XU, Zhangjie FU   +5 more
doaj   +3 more sources