Detecting and Localizing Adversarial Nodes Usig Neural Networks

Gangqiang Li, Sissi Xiaoxiao Wu, Shengli Zhang, Hoi To Wai, Anna Scaglione

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

Abstract

This work proposes a new method for securing the gossip algorithm for average consensus on communication networks. The gossip algorithm is appealing for its ability to harness distributed computational resources while adapting to arbitrarily connected networks without coordination overhead, however it is inherently vulnerable to the insider attack by adversarial node since each node locally updates its local states and passes information to its neighbors without supervision. In light of this, this work proposes new methods for detecting and localizing adversarial nodes using a neural network system. We show that our neural network-based method delivers a significantly improved detection and localization performance, compared to the state of the art.

Original languageEnglish (US)
Title of host publication2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Volume2018-June
ISBN (Print)9781538635124
DOIs
StatePublished - Aug 24 2018
Event19th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018 - Kalamata, Greece
Duration: Jun 25 2018Jun 28 2018

Other

Other19th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018
CountryGreece
CityKalamata
Period6/25/186/28/18

Fingerprint

Neural networks
Telecommunication networks

Keywords

  • average consensus
  • Gossip algorithm
  • insider attacks
  • neural networks

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Information Systems

Cite this

Li, G., Xiaoxiao Wu, S., Zhang, S., Wai, H. T., & Scaglione, A. (2018). Detecting and Localizing Adversarial Nodes Usig Neural Networks. In 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018 (Vol. 2018-June). [8445849] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SPAWC.2018.8445849

Detecting and Localizing Adversarial Nodes Usig Neural Networks. / Li, Gangqiang; Xiaoxiao Wu, Sissi; Zhang, Shengli; Wai, Hoi To; Scaglione, Anna.

2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018. Vol. 2018-June Institute of Electrical and Electronics Engineers Inc., 2018. 8445849.

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

Li, G, Xiaoxiao Wu, S, Zhang, S, Wai, HT & Scaglione, A 2018, Detecting and Localizing Adversarial Nodes Usig Neural Networks. in 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018. vol. 2018-June, 8445849, Institute of Electrical and Electronics Engineers Inc., 19th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018, Kalamata, Greece, 6/25/18. https://doi.org/10.1109/SPAWC.2018.8445849
Li G, Xiaoxiao Wu S, Zhang S, Wai HT, Scaglione A. Detecting and Localizing Adversarial Nodes Usig Neural Networks. In 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018. Vol. 2018-June. Institute of Electrical and Electronics Engineers Inc. 2018. 8445849 https://doi.org/10.1109/SPAWC.2018.8445849
Li, Gangqiang ; Xiaoxiao Wu, Sissi ; Zhang, Shengli ; Wai, Hoi To ; Scaglione, Anna. / Detecting and Localizing Adversarial Nodes Usig Neural Networks. 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018. Vol. 2018-June Institute of Electrical and Electronics Engineers Inc., 2018.
@inproceedings{6602f514f92d4e33baebce12dc9db27f,
title = "Detecting and Localizing Adversarial Nodes Usig Neural Networks",
abstract = "This work proposes a new method for securing the gossip algorithm for average consensus on communication networks. The gossip algorithm is appealing for its ability to harness distributed computational resources while adapting to arbitrarily connected networks without coordination overhead, however it is inherently vulnerable to the insider attack by adversarial node since each node locally updates its local states and passes information to its neighbors without supervision. In light of this, this work proposes new methods for detecting and localizing adversarial nodes using a neural network system. We show that our neural network-based method delivers a significantly improved detection and localization performance, compared to the state of the art.",
keywords = "average consensus, Gossip algorithm, insider attacks, neural networks",
author = "Gangqiang Li and {Xiaoxiao Wu}, Sissi and Shengli Zhang and Wai, {Hoi To} and Anna Scaglione",
year = "2018",
month = "8",
day = "24",
doi = "10.1109/SPAWC.2018.8445849",
language = "English (US)",
isbn = "9781538635124",
volume = "2018-June",
booktitle = "2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Detecting and Localizing Adversarial Nodes Usig Neural Networks

AU - Li, Gangqiang

AU - Xiaoxiao Wu, Sissi

AU - Zhang, Shengli

AU - Wai, Hoi To

AU - Scaglione, Anna

PY - 2018/8/24

Y1 - 2018/8/24

N2 - This work proposes a new method for securing the gossip algorithm for average consensus on communication networks. The gossip algorithm is appealing for its ability to harness distributed computational resources while adapting to arbitrarily connected networks without coordination overhead, however it is inherently vulnerable to the insider attack by adversarial node since each node locally updates its local states and passes information to its neighbors without supervision. In light of this, this work proposes new methods for detecting and localizing adversarial nodes using a neural network system. We show that our neural network-based method delivers a significantly improved detection and localization performance, compared to the state of the art.

AB - This work proposes a new method for securing the gossip algorithm for average consensus on communication networks. The gossip algorithm is appealing for its ability to harness distributed computational resources while adapting to arbitrarily connected networks without coordination overhead, however it is inherently vulnerable to the insider attack by adversarial node since each node locally updates its local states and passes information to its neighbors without supervision. In light of this, this work proposes new methods for detecting and localizing adversarial nodes using a neural network system. We show that our neural network-based method delivers a significantly improved detection and localization performance, compared to the state of the art.

KW - average consensus

KW - Gossip algorithm

KW - insider attacks

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=85053439423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053439423&partnerID=8YFLogxK

U2 - 10.1109/SPAWC.2018.8445849

DO - 10.1109/SPAWC.2018.8445849

M3 - Conference contribution

AN - SCOPUS:85053439423

SN - 9781538635124

VL - 2018-June

BT - 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -