Adding Security to Networks-on-Chip using Neural Networks

Kyle Madden; Jim Harkin; LJ McDaid; CD Nugent

doi:10.1109/ssci.2018.8628832

Adding Security to Networks-on-Chip using Neural Networks

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

23 Citations (Scopus)

15 Downloads (Pure)

Abstract

Modern computing systems are using Networks-on-Chip (NoCs) for scalable on-chip communications. Traditional security attacks have focused on the computing cores however modern attacks can focus on the NoC interconnect as a means to injecting unwanted traffic. This poses a significant security risk to physical systems that rely on sensory feedback and control signals. Malicious modification of these signals generates abnormal traffic patterns which affect the operation of the system and its performance. In this paper, we aim to identify abnormal traffic patterns (attacks) in Networks-on-Chip data through the use of Spiking Neural Networks. We explore the vulnerabilities of Denial-of-Service (DoS) attacks and report on evaluations to identify the impact of the duration of individual attacks on the rate of detection.

Keywords—Networks-on-Chip, Denial-of-Service, Security, Spiking Neural Networks, Pattern Recognition

Original language	English
Title of host publication	2018 IEEE Symposium Series on Computational Intelligence (SSCI)
DOIs	https://doi.org/10.1109/ssci.2018.8628832
Publication status	Published (in print/issue) - 15 Nov 2018

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities
SDG 16 Peace, Justice and Strong Institutions
SDG 17 Partnerships for the Goals

Keywords

Networks-on-Chip, Denial-of-Service, Security, Spiking Neural Networks, Pattern Recognition

Access to Document

10.1109/ssci.2018.8628832

SSCI_2018_accepted_versionAuthor Accepted Manuscript, 552 KB

Cite this

@inproceedings{8125b2ecbd974acf80f1488825f7e24b,

title = "Adding Security to Networks-on-Chip using Neural Networks",

abstract = "Modern computing systems are using Networks-on-Chip (NoCs) for scalable on-chip communications. Traditional security attacks have focused on the computing cores however modern attacks can focus on the NoC interconnect as a means to injecting unwanted traffic. This poses a significant security risk to physical systems that rely on sensory feedback and control signals. Malicious modification of these signals generates abnormal traffic patterns which affect the operation of the system and its performance. In this paper, we aim to identify abnormal traffic patterns (attacks) in Networks-on-Chip data through the use of Spiking Neural Networks. We explore the vulnerabilities of Denial-of-Service (DoS) attacks and report on evaluations to identify the impact of the duration of individual attacks on the rate of detection. Keywords—Networks-on-Chip, Denial-of-Service, Security, Spiking Neural Networks, Pattern Recognition",

keywords = "Networks-on-Chip, Denial-of-Service, Security, Spiking Neural Networks, Pattern Recognition",

author = "Kyle Madden and Jim Harkin and LJ McDaid and CD Nugent",

year = "2018",

month = nov,

day = "15",

doi = "10.1109/ssci.2018.8628832",

language = "English",

isbn = "9781538692769",

booktitle = "2018 IEEE Symposium Series on Computational Intelligence (SSCI)",

}

TY - GEN

T1 - Adding Security to Networks-on-Chip using Neural Networks

AU - Madden, Kyle

AU - Harkin, Jim

AU - McDaid, LJ

AU - Nugent, CD

PY - 2018/11/15

Y1 - 2018/11/15

N2 - Modern computing systems are using Networks-on-Chip (NoCs) for scalable on-chip communications. Traditional security attacks have focused on the computing cores however modern attacks can focus on the NoC interconnect as a means to injecting unwanted traffic. This poses a significant security risk to physical systems that rely on sensory feedback and control signals. Malicious modification of these signals generates abnormal traffic patterns which affect the operation of the system and its performance. In this paper, we aim to identify abnormal traffic patterns (attacks) in Networks-on-Chip data through the use of Spiking Neural Networks. We explore the vulnerabilities of Denial-of-Service (DoS) attacks and report on evaluations to identify the impact of the duration of individual attacks on the rate of detection. Keywords—Networks-on-Chip, Denial-of-Service, Security, Spiking Neural Networks, Pattern Recognition

AB - Modern computing systems are using Networks-on-Chip (NoCs) for scalable on-chip communications. Traditional security attacks have focused on the computing cores however modern attacks can focus on the NoC interconnect as a means to injecting unwanted traffic. This poses a significant security risk to physical systems that rely on sensory feedback and control signals. Malicious modification of these signals generates abnormal traffic patterns which affect the operation of the system and its performance. In this paper, we aim to identify abnormal traffic patterns (attacks) in Networks-on-Chip data through the use of Spiking Neural Networks. We explore the vulnerabilities of Denial-of-Service (DoS) attacks and report on evaluations to identify the impact of the duration of individual attacks on the rate of detection. Keywords—Networks-on-Chip, Denial-of-Service, Security, Spiking Neural Networks, Pattern Recognition

KW - Networks-on-Chip, Denial-of-Service, Security, Spiking Neural Networks, Pattern Recognition

UR - http://dx.doi.org/10.1109/ssci.2018.8628832

U2 - 10.1109/ssci.2018.8628832

DO - 10.1109/ssci.2018.8628832

M3 - Conference contribution

SN - 9781538692769

BT - 2018 IEEE Symposium Series on Computational Intelligence (SSCI)

ER -

Adding Security to Networks-on-Chip using Neural Networks

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Spiking neural networks for detecting denial-of-service attacks in networks-on-chip

Cite this

Adding Security to Networks-on-Chip using Neural Networks

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Student theses

Spiking neural networks for detecting denial-of-service attacks in networks-on-chip

Cite this