Defending Against Universal Attack Via Curvature-Aware Category Adversarial Training

Author:

Du Peilun1,Zheng Xiaolong1,Liu Liang1,Ma Huadong1

Affiliation:

1. Beijing University of Posts and Telecommunications,Beijing Key Lab of Intelligent Telecommunication Software and Multimedia,Beijing,China,100876

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China

Publisher

IEEE

Reference24 articles.

1. Defending Against Universal Attacks Through Selective Feature Regeneration

2. Towards deep learning models resistant to adversarial attacks;madry,2017

3. Adversarial training for free!;shafahi;Advances in neural information processing systems,2019

4. Fast is better than free: Revisiting adversarial training;wong,2020

5. Defense against adversarial attacks using feature scattering-based adversarial training;zhang;Advances in neural information processing systems,2019

Cited by 5 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. Physical Layer Identity Information Protection against Malicious Millimeter Wave Sensing;2023 IEEE Symposium on Computers and Communications (ISCC);2023-07-09

2. Class-Balanced Universal Perturbations for Adversarial Training;2023 International Joint Conference on Neural Networks (IJCNN);2023-06-18

3. LC-GAN: Improving Adversarial Robustness of Face Recognition Systems on Edge Devices;IEEE Internet of Things Journal;2023-05-01

4. WAIR: Watermark Attack on Image Retrieval Systems;2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS);2023-01

5. Defending Person Detection Against Adversarial Patch Attack by Using Universal Defensive Frame;IEEE Transactions on Image Processing;2022

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

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3