Evaluation and Detection of Hardware Trojan for Real-Time Many-Core Systems

Hazra, Suvadip; Sattenapalli, Jaswanth Sai; Roy, Arka; Dalui, Mamata

doi:10.1109/ised.2018.8703990

Cited by 5 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, [13] applied ML to detect flooding attacks. First, she extracted enough NoC-related attribute parameters and analyzed them for soundness; [14] selected a large number of NoC features and then used a large number of classification machine learning algorithms to detect hardware Trojans in order to achieve the best results, but sometimes there are oversaturation and detection efficiency is not high ; [15] focuses on using the threshold equation to detect HT, but he uses less machine learning and does not use different benchmark programs to test the effect; [16]'s work simulates four types of HT that can be stimulated by encountering specific conditions Hardware Trojans, using a decision tree, SVM and KNN to detect hardware Trojans respectively.…”

Section: Related Workmentioning

confidence: 99%

Cascaded Machine Learning Model Based DoS Attacks Detection and Classification in NoC

Wang

Halak

2023

2023 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Network-on-Chip (NoC) is becoming an increasingly common System-on-Chip (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 current detection methods becoming invalid. This paper presents a cascaded machine learning model based Denialof-Service (DoS) attack detection and classification approach. An Support Vector Machine (SVM) and a K-Nearest Neighbor (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 four traffic pattern cases. The proposed framework achieved an expected detection accuracy: more than 85% on detection in average. And outstanding classification results on every attack: 97% on Flooding, and up to 100% on both Routing Loop and Traffic Diversion.

show abstract