Cascaded Machine Learning Model Based DoS Attacks Detection and Classification in NoC
Cascaded Machine Learning Model Based DoS Attacks Detection and Classification in NoC
Network-on-Chip (NoC) is becoming an increasingly common SoC fabric architecture since it matches the characteristics of the SoC's shared storage and high-frequency communication. However, due to the rising utilization of NoC, a large number of adversaries are trying to inject hardware Trojan (HT) into NoC to obtain profits. An increasing variety of NoC HTs is emerging and implemented, resulting in detection methods becoming invalid. This paper presents a cascaded machine learning model-based Denial-of-Service (DoS) attack detection and classification approach. An SVM and a KNN model were employed in the framework, which has also been validated on our runtime mixed dataset consisting of normal and attacked data extracted from all traffic pattern cases. The proposed framework achieved an expected detection accuracy and outstanding classification results on every attack: 97% on Flooding, and up to 100% on both Routing Loop and Traffic Diversion.
Hu, Shengkai
5a753cff-0b9b-4004-b8b2-7aebb09d964a
Wang, Haoyu
3d04a266-1db2-42a6-9a4d-052c33c43873
Halak, Basel
8221f839-0dfd-4f81-9865-37def5f79f33
21 May 2023
Hu, Shengkai
5a753cff-0b9b-4004-b8b2-7aebb09d964a
Wang, Haoyu
3d04a266-1db2-42a6-9a4d-052c33c43873
Halak, Basel
8221f839-0dfd-4f81-9865-37def5f79f33
Hu, Shengkai, Wang, Haoyu and Halak, Basel
(2023)
Cascaded Machine Learning Model Based DoS Attacks Detection and Classification in NoC.
IEEE International Symposium on Circuits and Systems., Monterey, California, USA.
21 - 25 May 2023.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Network-on-Chip (NoC) is becoming an increasingly common SoC fabric architecture since it matches the characteristics of the SoC's shared storage and high-frequency communication. However, due to the rising utilization of NoC, a large number of adversaries are trying to inject hardware Trojan (HT) into NoC to obtain profits. An increasing variety of NoC HTs is emerging and implemented, resulting in detection methods becoming invalid. This paper presents a cascaded machine learning model-based Denial-of-Service (DoS) attack detection and classification approach. An SVM and a KNN model were employed in the framework, which has also been validated on our runtime mixed dataset consisting of normal and attacked data extracted from all traffic pattern cases. The proposed framework achieved an expected detection accuracy and outstanding classification results on every attack: 97% on Flooding, and up to 100% on both Routing Loop and Traffic Diversion.
Text
Cascaded machine learning model based DOs Attacks Detection and Classification in NoC
- Accepted Manuscript
Text
1664
- Version of Record
Restricted to Repository staff only
Request a copy
More information
Published date: 21 May 2023
Venue - Dates:
IEEE International Symposium on Circuits and Systems., Monterey, California, USA, 2023-05-21 - 2023-05-25
Identifiers
Local EPrints ID: 477364
URI: http://eprints.soton.ac.uk/id/eprint/477364
PURE UUID: 4f5b1952-2f37-4b14-bd9f-b9d1bdcc8d86
Catalogue record
Date deposited: 05 Jun 2023 16:44
Last modified: 17 Mar 2024 03:25
Export record
Contributors
Author:
Shengkai Hu
Author:
Haoyu Wang
Author:
Basel Halak
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics