Machine Learning in Adversarial Settings

Patrick McDaniel, Nicolas Papernot, Z. Berkay Celik

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

Recent advances in machine learning have led to innovative applications and services that use computational structures to reason about complex phenomenon. Over the past several years, the security and machine-learning communities have developed novel techniques for constructing adversarial samples-malicious inputs crafted to mislead (and therefore corrupt the integrity of) systems built on computationally learned models. The authors consider the underlying causes of adversarial samples and the future countermeasures that might mitigate them.

Original languageEnglish (US)
Article number7478523
Pages (from-to)68-72
Number of pages5
JournalIEEE Security and Privacy
Volume14
Issue number3
DOIs
StatePublished - May 1 2016

Fingerprint

Learning systems
learning
integrity
cause
community

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Law

Cite this

McDaniel, Patrick ; Papernot, Nicolas ; Celik, Z. Berkay. / Machine Learning in Adversarial Settings. In: IEEE Security and Privacy. 2016 ; Vol. 14, No. 3. pp. 68-72.
@article{3fec8ee77ce9482594565ff8bb4319f8,
title = "Machine Learning in Adversarial Settings",
abstract = "Recent advances in machine learning have led to innovative applications and services that use computational structures to reason about complex phenomenon. Over the past several years, the security and machine-learning communities have developed novel techniques for constructing adversarial samples-malicious inputs crafted to mislead (and therefore corrupt the integrity of) systems built on computationally learned models. The authors consider the underlying causes of adversarial samples and the future countermeasures that might mitigate them.",
author = "Patrick McDaniel and Nicolas Papernot and Celik, {Z. Berkay}",
year = "2016",
month = "5",
day = "1",
doi = "10.1109/MSP.2016.51",
language = "English (US)",
volume = "14",
pages = "68--72",
journal = "IEEE Security and Privacy",
issn = "1540-7993",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

McDaniel, P, Papernot, N & Celik, ZB 2016, 'Machine Learning in Adversarial Settings', IEEE Security and Privacy, vol. 14, no. 3, 7478523, pp. 68-72. https://doi.org/10.1109/MSP.2016.51

Machine Learning in Adversarial Settings. / McDaniel, Patrick; Papernot, Nicolas; Celik, Z. Berkay.

In: IEEE Security and Privacy, Vol. 14, No. 3, 7478523, 01.05.2016, p. 68-72.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine Learning in Adversarial Settings

AU - McDaniel, Patrick

AU - Papernot, Nicolas

AU - Celik, Z. Berkay

PY - 2016/5/1

Y1 - 2016/5/1

N2 - Recent advances in machine learning have led to innovative applications and services that use computational structures to reason about complex phenomenon. Over the past several years, the security and machine-learning communities have developed novel techniques for constructing adversarial samples-malicious inputs crafted to mislead (and therefore corrupt the integrity of) systems built on computationally learned models. The authors consider the underlying causes of adversarial samples and the future countermeasures that might mitigate them.

AB - Recent advances in machine learning have led to innovative applications and services that use computational structures to reason about complex phenomenon. Over the past several years, the security and machine-learning communities have developed novel techniques for constructing adversarial samples-malicious inputs crafted to mislead (and therefore corrupt the integrity of) systems built on computationally learned models. The authors consider the underlying causes of adversarial samples and the future countermeasures that might mitigate them.

UR - http://www.scopus.com/inward/record.url?scp=84973354134&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973354134&partnerID=8YFLogxK

U2 - 10.1109/MSP.2016.51

DO - 10.1109/MSP.2016.51

M3 - Article

AN - SCOPUS:84973354134

VL - 14

SP - 68

EP - 72

JO - IEEE Security and Privacy

JF - IEEE Security and Privacy

SN - 1540-7993

IS - 3

M1 - 7478523

ER -