Towards Backdoor Attacks and Defense in Robust Machine Learning Models

Author:

Soremekun EzekielORCID,Udeshi Sakshi,Chattopadhyay SudiptaORCID

Publisher

Elsevier BV

Subject

Law,General Computer Science

Reference74 articles.

1. Robustness to adversarial examples through an ensemble of specialists;Abbasi;arXiv preprint arXiv:1702.06856,2017

2. Blind backdoors in deep learning models;Bagdasaryan;arXiv preprint arXiv:2005.03823,2020

3. Detecting backdoor attacks on deep neural networks by activation clustering;Chen,2019

4. Sentinet: Detecting physical attacks against deep learning systems;Chou;arXiv preprint arXiv:1812.00292,2018

5. Robustbench: a standardized adversarial robustness benchmark;Croce;arXiv preprint arXiv:2010.09670,2020

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. Securing Machine Learning: Understanding Adversarial Attacks and Bias Mitigation;International Journal of Innovative Science and Research Technology (IJISRT);2024-07-11

2. Data Poisoning Attacks in Cognitive Computing;2024 IEEE 9th International Conference for Convergence in Technology (I2CT);2024-04-05

3. Backdoor attack detection via prediction trustworthiness assessment;Information Sciences;2024-03

4. Extent of spending behavior, problems encountered, and financial knowledge across generational cohorts among state universities and colleges employees;International Journal of ADVANCED AND APPLIED SCIENCES;2024-02

5. Exploring Clean Label Backdoor Attacks and Defense in Language Models;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2024

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