Visual Prompting for Adversarial Robustness

Author:

Chen Aochuan1,Lorenz Peter2,Yao Yuguang1,Chen Pin-Yu3,Liu Sijia1

Affiliation:

1. Michigan State University,USA

2. Fraunhofer ITWM and Fraunhofer Center of Machine Learning,Germany

3. IBM Research,USA

Publisher

IEEE

Reference46 articles.

1. Evaluating the adversarial robustness of adaptive test-time defenses;croce;arXiv 2202 13711,2022

2. On detecting adversarial perturbations;metzen;arXiv 1702 04267,2017

3. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks;croce;ICML,2020

4. Ml-loo: Detecting adversarial examples with feature attribution;yang;arXiv 1906 03499,2019

5. Adversarial Attacks are Reversible with Natural Supervision

Cited by 4 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 Machine Learning for Social Good: Reframing the Adversary as an Ally;IEEE Transactions on Artificial Intelligence;2024-09

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

3. Exploring the Benefits of Visual Prompting in Differential Privacy;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

4. Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

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