A Feature-Based On-Line Detector to Remove Adversarial-Backdoors by Iterative Demarcation-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

A Feature-Based On-Line Detector to Remove Adversarial-Backdoors by Iterative Demarcation

Published:2022 Issue: Volume:10 Page:5545-5558
ISSN:2169-3536
Container-title:IEEE Access
language:
Short-container-title:IEEE Access

Author:

Fu Hao^ORCID,Veldanda Akshaj Kumar,Krishnamurthy Prashanth^ORCID,Garg Siddharth^ORCID,Khorrami Farshad^ORCID

Funder

Army Research Office

New York University (NYU) Abu Dhabi Center in Artificial Intelligence (AI) and Robotics

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

General Engineering,General Materials Science,General Computer Science

Link

http://xplorestaging.ieee.org/ielx7/6287639/9668973/09673744.pdf?arnumber=9673744

Reference77 articles.

1. ImageNet: A large-scale hierarchical image database

2. Face recognition in unconstrained videos with matched background similarity

3. Learning multiple layers of features from tiny images;krizhevsky,2009

4. Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition

5. FaceHack: Triggering backdoored facial recognition systems using facial characteristics;sarkar;arXiv 2006 11623,2020

Cited by 8 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. UCM-Net: A lightweight and efficient solution for skin lesion segmentation using MLP and CNN;Biomedical Signal Processing and Control;2024-10

2. Invisible backdoor learning in regional transform domain;Neural Computing and Applications;2024-02-28

3. A Comprehensive Survey on Backdoor Attacks and Their Defenses in Face Recognition Systems;IEEE Access;2024

4. Backdoor Attacks to Deep Neural Networks: A Survey of the Literature, Challenges, and Future Research Directions;IEEE Access;2024

5. Mitigating Backdoor Attacks on Deep Neural Networks;Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing;2023-10-07

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

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