AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learning
Author:
Affiliation:
1. Stony Brook University,Stony Brook,NY,USA
2. Brookhaven National Laboratory,Upton,NY,USA
Funder
U.S. Department of Energy
Office of Science
High Energy Physics
Brookhaven National Laboratory
National Science Foundation
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9709627/9709628/09711039.pdf?arnumber=9711039
Reference53 articles.
1. Are labels required for improving adversarial robustness?;uesato;NeurIPS,2019
2. Intriguing properties of neural networks;szegedy;ICLRE,2014
3. Overfitting in adversarially robust deep learning;rice;ICML,2020
4. Bit-Flip Attack: Crushing Neural Network With Progressive Bit Search
5. The Limitations of Deep Learning in Adversarial Settings
Cited by 11 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. Like teacher, like pupil: Transferring backdoors via feature-based knowledge distillation;Computers & Security;2024-11
2. Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-10
3. Exploring Robust Features for Improving Adversarial Robustness;IEEE Transactions on Cybernetics;2024-09
4. Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detection;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03
5. A Robust Adversarial Defense Algorithm for Enhancing Salient Object Detection in Remote Sensing Image;IEEE Transactions on Geoscience and Remote Sensing;2024
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