SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain

Published:2021-07-18 Issue: Volume: Page:
ISSN:
Container-title:2021 International Joint Conference on Neural Networks (IJCNN)
language:
Short-container-title:

Author:

Harder Paula¹,Pfreundt Franz-Josef¹,Keuper Margret²,Keuper Janis³

Affiliation:

1. Competence Center High Performance Computing, Fraunhofer ITWM,Kaiserslautern,Germany

2. Data and Web Science Group, University of Mannheim,Germany

3. Institute for Machine Learning and Analytics (IMLA), Offenburg University,Germany

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9533266/9533267/09533442.pdf?arnumber=9533442

Cited by 29 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Adversarial example denoising and detection based on the consistency between Fourier-transformed layers;Neurocomputing;2024-11

2. Leveraging AutoEncoders and chaos theory to improve adversarial example detection;Neural Computing and Applications;2024-07-24

3. Feature Decoupling Based Adversarial Examples Detection Method for Remote Sensing Scene Classification;IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium;2024-07-07

4. Adversarial Examples are Misaligned in Diffusion Model Manifolds;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

5. An AI blue team playbook;Assurance and Security for AI-enabled Systems;2024-06-07

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP