Detection of data injection attacks in decentralized learning

Reinhard Gentz, Hoi To Wai, Anna Scaglione, Amir Leshem

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

2 Citations (Scopus)

Abstract

Gossip based optimization and learning are appealing methods that solve big data learning problems sharing computation and network resources when data are distributed. The main advantage these methods offer is that they are fault tolerant. Their flat architecture, however, expands the attack surface in the case of a data injection attack. We analyze the effects of data injection on the asymptotic behavior of the network and draw a parallel with the case of opinion dynamics in a network where zealots inject opinions to mislead a community. We further propose a possible decentralized detection of such attacks and analyze its performance.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
PublisherIEEE Computer Society
Pages350-354
Number of pages5
Volume2016-February
ISBN (Print)9781467385763
DOIs
StatePublished - Feb 26 2016
Event49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 - Pacific Grove, United States
Duration: Nov 8 2015Nov 11 2015

Other

Other49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015
CountryUnited States
CityPacific Grove
Period11/8/1511/11/15

Fingerprint

Big data

Keywords

  • attack detection
  • data injection attack
  • decentralized learning
  • randomized gossip protocol

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Gentz, R., Wai, H. T., Scaglione, A., & Leshem, A. (2016). Detection of data injection attacks in decentralized learning. In Conference Record - Asilomar Conference on Signals, Systems and Computers (Vol. 2016-February, pp. 350-354). [7421145] IEEE Computer Society. https://doi.org/10.1109/ACSSC.2015.7421145

Detection of data injection attacks in decentralized learning. / Gentz, Reinhard; Wai, Hoi To; Scaglione, Anna; Leshem, Amir.

Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2016-February IEEE Computer Society, 2016. p. 350-354 7421145.

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

Gentz, R, Wai, HT, Scaglione, A & Leshem, A 2016, Detection of data injection attacks in decentralized learning. in Conference Record - Asilomar Conference on Signals, Systems and Computers. vol. 2016-February, 7421145, IEEE Computer Society, pp. 350-354, 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015, Pacific Grove, United States, 11/8/15. https://doi.org/10.1109/ACSSC.2015.7421145
Gentz R, Wai HT, Scaglione A, Leshem A. Detection of data injection attacks in decentralized learning. In Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2016-February. IEEE Computer Society. 2016. p. 350-354. 7421145 https://doi.org/10.1109/ACSSC.2015.7421145
Gentz, Reinhard ; Wai, Hoi To ; Scaglione, Anna ; Leshem, Amir. / Detection of data injection attacks in decentralized learning. Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2016-February IEEE Computer Society, 2016. pp. 350-354
@inproceedings{dfbdd7023f744f26b1f52b9f4d057536,
title = "Detection of data injection attacks in decentralized learning",
abstract = "Gossip based optimization and learning are appealing methods that solve big data learning problems sharing computation and network resources when data are distributed. The main advantage these methods offer is that they are fault tolerant. Their flat architecture, however, expands the attack surface in the case of a data injection attack. We analyze the effects of data injection on the asymptotic behavior of the network and draw a parallel with the case of opinion dynamics in a network where zealots inject opinions to mislead a community. We further propose a possible decentralized detection of such attacks and analyze its performance.",
keywords = "attack detection, data injection attack, decentralized learning, randomized gossip protocol",
author = "Reinhard Gentz and Wai, {Hoi To} and Anna Scaglione and Amir Leshem",
year = "2016",
month = "2",
day = "26",
doi = "10.1109/ACSSC.2015.7421145",
language = "English (US)",
isbn = "9781467385763",
volume = "2016-February",
pages = "350--354",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Detection of data injection attacks in decentralized learning

AU - Gentz, Reinhard

AU - Wai, Hoi To

AU - Scaglione, Anna

AU - Leshem, Amir

PY - 2016/2/26

Y1 - 2016/2/26

N2 - Gossip based optimization and learning are appealing methods that solve big data learning problems sharing computation and network resources when data are distributed. The main advantage these methods offer is that they are fault tolerant. Their flat architecture, however, expands the attack surface in the case of a data injection attack. We analyze the effects of data injection on the asymptotic behavior of the network and draw a parallel with the case of opinion dynamics in a network where zealots inject opinions to mislead a community. We further propose a possible decentralized detection of such attacks and analyze its performance.

AB - Gossip based optimization and learning are appealing methods that solve big data learning problems sharing computation and network resources when data are distributed. The main advantage these methods offer is that they are fault tolerant. Their flat architecture, however, expands the attack surface in the case of a data injection attack. We analyze the effects of data injection on the asymptotic behavior of the network and draw a parallel with the case of opinion dynamics in a network where zealots inject opinions to mislead a community. We further propose a possible decentralized detection of such attacks and analyze its performance.

KW - attack detection

KW - data injection attack

KW - decentralized learning

KW - randomized gossip protocol

UR - http://www.scopus.com/inward/record.url?scp=84969836578&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969836578&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2015.7421145

DO - 10.1109/ACSSC.2015.7421145

M3 - Conference contribution

AN - SCOPUS:84969836578

SN - 9781467385763

VL - 2016-February

SP - 350

EP - 354

BT - Conference Record - Asilomar Conference on Signals, Systems and Computers

PB - IEEE Computer Society

ER -