Adversarial learning: A critical review and active learning study

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This papers consists of two parts. The first is a critical review of prior art on adversarial learning, i) identifying some significant limitations of previous works, which have focused mainly on attack exploits and ii) proposing novel defenses against adversarial attacks. The second part is an experimental study considering the adversarial active learning scenario and an investigation of the efficacy of a mixed sample selection strategy for combating an adversary who attempts to disrupt the classifier learning.

Original languageEnglish (US)
Title of host publication2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings
EditorsNaonori Ueda, Jen-Tzung Chien, Tomoko Matsui, Jan Larsen, Shinji Watanabe
PublisherIEEE Computer Society
Pages1-6
Number of pages6
ISBN (Electronic)9781509063413
DOIs
StatePublished - Dec 5 2017
Event2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Tokyo, Japan
Duration: Sep 25 2017Sep 28 2017

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2017-September
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Other

Other2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017
CountryJapan
CityTokyo
Period9/25/179/28/17

Fingerprint

Classifiers
Problem-Based Learning

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Signal Processing

Cite this

Miller, D. J., Hu, X., Qiu, Z., & Kesidis, G. (2017). Adversarial learning: A critical review and active learning study. In N. Ueda, J-T. Chien, T. Matsui, J. Larsen, & S. Watanabe (Eds.), 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings (pp. 1-6). (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2017-September). IEEE Computer Society. https://doi.org/10.1109/MLSP.2017.8168163
Miller, David Jonathan ; Hu, X. ; Qiu, Z. ; Kesidis, George. / Adversarial learning : A critical review and active learning study. 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings. editor / Naonori Ueda ; Jen-Tzung Chien ; Tomoko Matsui ; Jan Larsen ; Shinji Watanabe. IEEE Computer Society, 2017. pp. 1-6 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).
@inproceedings{469364f06cde4aa5904f1917d3b54284,
title = "Adversarial learning: A critical review and active learning study",
abstract = "This papers consists of two parts. The first is a critical review of prior art on adversarial learning, i) identifying some significant limitations of previous works, which have focused mainly on attack exploits and ii) proposing novel defenses against adversarial attacks. The second part is an experimental study considering the adversarial active learning scenario and an investigation of the efficacy of a mixed sample selection strategy for combating an adversary who attempts to disrupt the classifier learning.",
author = "Miller, {David Jonathan} and X. Hu and Z. Qiu and George Kesidis",
year = "2017",
month = "12",
day = "5",
doi = "10.1109/MLSP.2017.8168163",
language = "English (US)",
series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",
publisher = "IEEE Computer Society",
pages = "1--6",
editor = "Naonori Ueda and Jen-Tzung Chien and Tomoko Matsui and Jan Larsen and Shinji Watanabe",
booktitle = "2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings",
address = "United States",

}

Miller, DJ, Hu, X, Qiu, Z & Kesidis, G 2017, Adversarial learning: A critical review and active learning study. in N Ueda, J-T Chien, T Matsui, J Larsen & S Watanabe (eds), 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings. IEEE International Workshop on Machine Learning for Signal Processing, MLSP, vol. 2017-September, IEEE Computer Society, pp. 1-6, 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017, Tokyo, Japan, 9/25/17. https://doi.org/10.1109/MLSP.2017.8168163

Adversarial learning : A critical review and active learning study. / Miller, David Jonathan; Hu, X.; Qiu, Z.; Kesidis, George.

2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings. ed. / Naonori Ueda; Jen-Tzung Chien; Tomoko Matsui; Jan Larsen; Shinji Watanabe. IEEE Computer Society, 2017. p. 1-6 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2017-September).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Adversarial learning

T2 - A critical review and active learning study

AU - Miller, David Jonathan

AU - Hu, X.

AU - Qiu, Z.

AU - Kesidis, George

PY - 2017/12/5

Y1 - 2017/12/5

N2 - This papers consists of two parts. The first is a critical review of prior art on adversarial learning, i) identifying some significant limitations of previous works, which have focused mainly on attack exploits and ii) proposing novel defenses against adversarial attacks. The second part is an experimental study considering the adversarial active learning scenario and an investigation of the efficacy of a mixed sample selection strategy for combating an adversary who attempts to disrupt the classifier learning.

AB - This papers consists of two parts. The first is a critical review of prior art on adversarial learning, i) identifying some significant limitations of previous works, which have focused mainly on attack exploits and ii) proposing novel defenses against adversarial attacks. The second part is an experimental study considering the adversarial active learning scenario and an investigation of the efficacy of a mixed sample selection strategy for combating an adversary who attempts to disrupt the classifier learning.

UR - http://www.scopus.com/inward/record.url?scp=85042313775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042313775&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2017.8168163

DO - 10.1109/MLSP.2017.8168163

M3 - Conference contribution

AN - SCOPUS:85042313775

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

SP - 1

EP - 6

BT - 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings

A2 - Ueda, Naonori

A2 - Chien, Jen-Tzung

A2 - Matsui, Tomoko

A2 - Larsen, Jan

A2 - Watanabe, Shinji

PB - IEEE Computer Society

ER -

Miller DJ, Hu X, Qiu Z, Kesidis G. Adversarial learning: A critical review and active learning study. In Ueda N, Chien J-T, Matsui T, Larsen J, Watanabe S, editors, 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings. IEEE Computer Society. 2017. p. 1-6. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). https://doi.org/10.1109/MLSP.2017.8168163