A game-theoretic analysis of label flipping attacks on distributed support vector machines

Rui Zhang, Quanyan Zhu

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

Abstract

Distributed machine learning algorithms play a significant role in processing massive data sets over large networks. However, the increasing reliance on machine learning on information and communication technologies makes it inherently vulnerable to cyber threats. This work aims to develop secure distributed algorithms to protect the learning from adversaries. We establish a game-theoretic framework to capture the conflicting goals of a learner who uses distributed support vector machines (DSVM) and an attacker who is capable of flipping training labels. We develop a fully distributed and iterative algorithm to capture real-time reactions of the learner at each node to adversarial behaviors. The numerical results show that DSVM is vulnerable to attacks, and their impact has a strong dependence on the network topologies.

Original languageEnglish (US)
Title of host publication2017 51st Annual Conference on Information Sciences and Systems, CISS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509047802
DOIs
StatePublished - May 10 2017
Event51st Annual Conference on Information Sciences and Systems, CISS 2017 - Baltimore, United States
Duration: Mar 22 2017Mar 24 2017

Other

Other51st Annual Conference on Information Sciences and Systems, CISS 2017
CountryUnited States
CityBaltimore
Period3/22/173/24/17

Fingerprint

Support vector machines
Learning systems
Labels
Parallel algorithms
Learning algorithms
Topology
Communication
Support vector machine
Attack
Machine learning

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems and Management
  • Computer Networks and Communications
  • Information Systems

Cite this

Zhang, R., & Zhu, Q. (2017). A game-theoretic analysis of label flipping attacks on distributed support vector machines. In 2017 51st Annual Conference on Information Sciences and Systems, CISS 2017 [7926118] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CISS.2017.7926118

A game-theoretic analysis of label flipping attacks on distributed support vector machines. / Zhang, Rui; Zhu, Quanyan.

2017 51st Annual Conference on Information Sciences and Systems, CISS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 7926118.

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

Zhang, R & Zhu, Q 2017, A game-theoretic analysis of label flipping attacks on distributed support vector machines. in 2017 51st Annual Conference on Information Sciences and Systems, CISS 2017., 7926118, Institute of Electrical and Electronics Engineers Inc., 51st Annual Conference on Information Sciences and Systems, CISS 2017, Baltimore, United States, 3/22/17. https://doi.org/10.1109/CISS.2017.7926118
Zhang R, Zhu Q. A game-theoretic analysis of label flipping attacks on distributed support vector machines. In 2017 51st Annual Conference on Information Sciences and Systems, CISS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 7926118 https://doi.org/10.1109/CISS.2017.7926118
Zhang, Rui ; Zhu, Quanyan. / A game-theoretic analysis of label flipping attacks on distributed support vector machines. 2017 51st Annual Conference on Information Sciences and Systems, CISS 2017. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{0dd57fbd3dcf495682e34ec33043ec82,
title = "A game-theoretic analysis of label flipping attacks on distributed support vector machines",
abstract = "Distributed machine learning algorithms play a significant role in processing massive data sets over large networks. However, the increasing reliance on machine learning on information and communication technologies makes it inherently vulnerable to cyber threats. This work aims to develop secure distributed algorithms to protect the learning from adversaries. We establish a game-theoretic framework to capture the conflicting goals of a learner who uses distributed support vector machines (DSVM) and an attacker who is capable of flipping training labels. We develop a fully distributed and iterative algorithm to capture real-time reactions of the learner at each node to adversarial behaviors. The numerical results show that DSVM is vulnerable to attacks, and their impact has a strong dependence on the network topologies.",
author = "Rui Zhang and Quanyan Zhu",
year = "2017",
month = "5",
day = "10",
doi = "10.1109/CISS.2017.7926118",
language = "English (US)",
booktitle = "2017 51st Annual Conference on Information Sciences and Systems, CISS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - A game-theoretic analysis of label flipping attacks on distributed support vector machines

AU - Zhang, Rui

AU - Zhu, Quanyan

PY - 2017/5/10

Y1 - 2017/5/10

N2 - Distributed machine learning algorithms play a significant role in processing massive data sets over large networks. However, the increasing reliance on machine learning on information and communication technologies makes it inherently vulnerable to cyber threats. This work aims to develop secure distributed algorithms to protect the learning from adversaries. We establish a game-theoretic framework to capture the conflicting goals of a learner who uses distributed support vector machines (DSVM) and an attacker who is capable of flipping training labels. We develop a fully distributed and iterative algorithm to capture real-time reactions of the learner at each node to adversarial behaviors. The numerical results show that DSVM is vulnerable to attacks, and their impact has a strong dependence on the network topologies.

AB - Distributed machine learning algorithms play a significant role in processing massive data sets over large networks. However, the increasing reliance on machine learning on information and communication technologies makes it inherently vulnerable to cyber threats. This work aims to develop secure distributed algorithms to protect the learning from adversaries. We establish a game-theoretic framework to capture the conflicting goals of a learner who uses distributed support vector machines (DSVM) and an attacker who is capable of flipping training labels. We develop a fully distributed and iterative algorithm to capture real-time reactions of the learner at each node to adversarial behaviors. The numerical results show that DSVM is vulnerable to attacks, and their impact has a strong dependence on the network topologies.

UR - http://www.scopus.com/inward/record.url?scp=85020223548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020223548&partnerID=8YFLogxK

U2 - 10.1109/CISS.2017.7926118

DO - 10.1109/CISS.2017.7926118

M3 - Conference contribution

BT - 2017 51st Annual Conference on Information Sciences and Systems, CISS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -