Properties that allow or prohibit transferability of adversarial attacks among quantized networks

Author:

Shrestha Abhishek1ORCID,Großmann Jürgen1ORCID

Affiliation:

1. Fraunhofer-Institut für Offene Kommunikationssysteme FOKUS, Berlin, Germany

Funder

German Federal Ministry for Economic Affairs and Climate Action (KI-LOK project)

German Federal Ministry for Education and Research (IML4E project)

Publisher

ACM

Reference36 articles.

1. Yoshua Bengio Nicholas Leonard and Aaron Courville. 2013. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. (2013). arXiv:1308.3432 http://arxiv.org/abs/1308.3432

2. Impact of Low-Bitwidth Quantization on the Adversarial Robustness for Embedded Neural Networks

3. Wieland Brendel Jonas Rauber and Matthias Bethge. 2018. Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models. (2018). arXiv:1712.04248 http://arxiv.org/abs/1712.04248

4. Towards Evaluating the Robustness of Neural Networks

5. Ambra Demontis Marco Melis Maura Pintor Matthew Jagielski Battista Biggio Alina Oprea Cristina Nita-Rotaru and Fabio Roli. 2019. Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks. (2019) 19.

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