On The Existence of The Adversarial Bayes Classifier

Pranjal Awasthi; Natalie S. Frank; Mehryar Mohri

On The Existence of The Adversarial Bayes Classifier

Pranjal Awasthi, Natalie S. Frank, Mehryar Mohri

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many important questions related to adversarial robustness are still open. In this work, we study a fundamental question regarding Bayes optimality for adversarial robustness. We provide general sufficient conditions under which the existence of a Bayes optimal classifier can be guaranteed for adversarial robustness. Our results can provide a useful tool for a subsequent study of surrogate losses in adversarial robustness and their consistency properties.

Original language	English (US)
Title of host publication	Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
Editors	Marc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
Publisher	Neural information processing systems foundation
Pages	2978-2990
Number of pages	13
ISBN (Electronic)	9781713845393
State	Published - 2021
Event	35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online Duration: Dec 6 2021 → Dec 14 2021

Publication series

Name	Advances in Neural Information Processing Systems
Volume	4
ISSN (Print)	1049-5258

Conference

Conference	35th Conference on Neural Information Processing Systems, NeurIPS 2021
City	Virtual, Online
Period	12/6/21 → 12/14/21

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

Awasthi, P., Frank, N. S., & Mohri, M. (2021). On The Existence of The Adversarial Bayes Classifier. In MA. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, & J. Wortman Vaughan (Eds.), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 (pp. 2978-2990). (Advances in Neural Information Processing Systems; Vol. 4). Neural information processing systems foundation.

On The Existence of The Adversarial Bayes Classifier. / Awasthi, Pranjal; Frank, Natalie S.; Mohri, Mehryar.
Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. ed. / Marc'Aurelio Ranzato; Alina Beygelzimer; Yann Dauphin; Percy S. Liang; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. p. 2978-2990 (Advances in Neural Information Processing Systems; Vol. 4).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Awasthi, P, Frank, NS & Mohri, M 2021, On The Existence of The Adversarial Bayes Classifier. in MA Ranzato, A Beygelzimer, Y Dauphin, PS Liang & J Wortman Vaughan (eds), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Advances in Neural Information Processing Systems, vol. 4, Neural information processing systems foundation, pp. 2978-2990, 35th Conference on Neural Information Processing Systems, NeurIPS 2021, Virtual, Online, 12/6/21.

Awasthi P, Frank NS, Mohri M. On The Existence of The Adversarial Bayes Classifier. In Ranzato MA, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors, Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Neural information processing systems foundation. 2021. p. 2978-2990. (Advances in Neural Information Processing Systems).

Awasthi, Pranjal ; Frank, Natalie S. ; Mohri, Mehryar. / On The Existence of The Adversarial Bayes Classifier. Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. editor / Marc'Aurelio Ranzato ; Alina Beygelzimer ; Yann Dauphin ; Percy S. Liang ; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. pp. 2978-2990 (Advances in Neural Information Processing Systems).

@inproceedings{d43341597a824ded8509e8abac02eb41,

title = "On The Existence of The Adversarial Bayes Classifier",

abstract = "Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many important questions related to adversarial robustness are still open. In this work, we study a fundamental question regarding Bayes optimality for adversarial robustness. We provide general sufficient conditions under which the existence of a Bayes optimal classifier can be guaranteed for adversarial robustness. Our results can provide a useful tool for a subsequent study of surrogate losses in adversarial robustness and their consistency properties.",

author = "Pranjal Awasthi and Frank, {Natalie S.} and Mehryar Mohri",

note = "Funding Information: This work was partly funded by NSF CCF-1535987 and NSF IIS-1618662. Special thanks to Professor James A. Morrow for some useful pointers on measurability. Publisher Copyright: {\textcopyright} 2021 Neural information processing systems foundation. All rights reserved.; 35th Conference on Neural Information Processing Systems, NeurIPS 2021 ; Conference date: 06-12-2021 Through 14-12-2021",

year = "2021",

language = "English (US)",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "2978--2990",

editor = "Marc'Aurelio Ranzato and Alina Beygelzimer and Yann Dauphin and Liang, {Percy S.} and {Wortman Vaughan}, Jenn",

booktitle = "Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021",

}

TY - GEN

T1 - On The Existence of The Adversarial Bayes Classifier

AU - Awasthi, Pranjal

AU - Frank, Natalie S.

AU - Mohri, Mehryar

N1 - Funding Information: This work was partly funded by NSF CCF-1535987 and NSF IIS-1618662. Special thanks to Professor James A. Morrow for some useful pointers on measurability. Publisher Copyright: © 2021 Neural information processing systems foundation. All rights reserved.

PY - 2021

Y1 - 2021

N2 - Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many important questions related to adversarial robustness are still open. In this work, we study a fundamental question regarding Bayes optimality for adversarial robustness. We provide general sufficient conditions under which the existence of a Bayes optimal classifier can be guaranteed for adversarial robustness. Our results can provide a useful tool for a subsequent study of surrogate losses in adversarial robustness and their consistency properties.

AB - Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many important questions related to adversarial robustness are still open. In this work, we study a fundamental question regarding Bayes optimality for adversarial robustness. We provide general sufficient conditions under which the existence of a Bayes optimal classifier can be guaranteed for adversarial robustness. Our results can provide a useful tool for a subsequent study of surrogate losses in adversarial robustness and their consistency properties.

UR - http://www.scopus.com/inward/record.url?scp=85121130400&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85121130400&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85121130400

T3 - Advances in Neural Information Processing Systems

SP - 2978

EP - 2990

BT - Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

A2 - Ranzato, Marc'Aurelio

A2 - Beygelzimer, Alina

A2 - Dauphin, Yann

A2 - Liang, Percy S.

A2 - Wortman Vaughan, Jenn

PB - Neural information processing systems foundation

T2 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

Y2 - 6 December 2021 through 14 December 2021

ER -

On The Existence of The Adversarial Bayes Classifier

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this