A Novel Golden Models-Free Hardware Trojan Detection Technique Using Unsupervised Clustering Analysis

Bian, Rongzhen; Xue, Mingfu; Wang, Jian

doi:10.1007/978-3-030-00015-8_55

Cited by 8 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each subset is referred as a cluster [27]. In [24], we have formulated the unsupervised hardware Trojan detection problem into two types of clustering based detection models, i.e., the partition-based model and the density-based model.…”

Section: Preliminary a Unsupervised Hardware Trojan Detection Methods Using Clustering Analysismentioning

confidence: 99%

“…Motivated by the above problems, we have proposed an unsupervised golden models-free hardware Trojan detection method using clustering analysis [24] which will be described in Section II-A as the preliminary. In [24], the major contribution is that we formulate the unsupervised hardware Trojan detection problem into two types of clustering based hardware Trojan detection models, the partition-based model and the density-based model. Then we exploit a clustering algorithm for unsupervised hardware Trojan detection to eliminate the need of simulated golden models and fabricated golden chips.…”

Section: Introductionmentioning

confidence: 99%

“…Then we exploit a clustering algorithm for unsupervised hardware Trojan detection to eliminate the need of simulated golden models and fabricated golden chips. A cluster labeling index (CMI ) is proposed to identify which cluster is genuine [24]. The test performance of the method is evaluated with EDA experiments.…”

Section: Introductionmentioning

confidence: 99%

“…The test performance of the method is evaluated with EDA experiments. However, in existing hardware Trojan detection works, including [24], the testing party is considered as trustworthy. Therefore, in the conference version of this work [25], we are the first to consider that the testing party may be untrustworthy, and we propose a clustering ensemble based hardware Trojan detection method to defeat untrustworthy testing parties [25], which can also improve the test performance of the basic clustering algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Defeating Untrustworthy Testing Parties: A Novel Hybrid Clustering Ensemble Based Golden Models-Free Hardware Trojan Detection Method

et al. 2019

Self Cite

View full text Add to dashboard Cite

Due to the globalization of the design and fabrication process of integrated circuits (ICs), ICs are becoming vulnerable to hardware Trojans. Most of the existing hardware Trojan detection works assume that the testing stage is trustworthy. However, testing parties may collude with malicious attackers and modify the results of hardware Trojan detection. In this paper, two attack models for untrustworthy testing parties are formulated. We further propose an adversarial data generation method for untrustworthy testing parties to modify the collected test data. Then, we propose a novel hybrid clustering ensemble method to build a trusted hardware Trojan detection method (clustering ensemble-based hardware Trojan detection method) against untrustworthy testing parties. To alleviate the impact of process variations and noises on hardware Trojan detection in the actual measurement, the unsupervised correlation-based feature selection method is exploited to process the raw test data of ICs for feature selection. The proposed method can eliminate the need of the fabricated golden chips and the simulated golden models. It can also resist the malicious modifications on Trojan detection results introduced by untrustworthy testing parties. Besides, the following problems and questions are also theoretically analyzed and answered: 1) the number of necessary testing parties; 2) the time overhead and the computational overhead of the proposed method; 3) how to choose the basic clustering algorithms (by using a proposed diversity analysis algorithm); and 4) the reason why the proposed clustering ensemble method is superior to the majority voting method. Both the EDA evaluation on ISCAS89 benchmarks and field-programmable gate array evaluation on Trust-HUB benchmarks are performed to evaluate the performance of the proposed method. Experimental results demonstrate that the proposed method can resist malicious modifications robustly and can detect hardware Trojans with high accuracy (up to 93.75%). Meanwhile, the introduced time overhead is small. INDEX TERMS Hardware security, hardware Trojan detection, untrustworthy testing parties, unsupervised learning, clustering ensemble.

show abstract

Section: Preliminary a Unsupervised Hardware Trojan Detection Methods Using Clustering Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Defeating Untrustworthy Testing Parties: A Novel Hybrid Clustering Ensemble Based Golden Models-Free Hardware Trojan Detection Method

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent research in this field has explored machine learning methods for HT detection [41, 88–90, 105–111]. Generally, machine learning methods can be utilised for HT detection in the following aspects: providing automatic layout identification in RE‐based methods [88, 105, 106], providing run‐time HT detection architectures, which are trained by HT attack behaviours [107, 108], providing automatic feature analysis [112], and providing golden chips‐free HT detection techniques based on classification or clustering [41, 89, 90, 109–111]. In particular, the machine learning method has its own specialties in feature extraction and image recognition, which makes it possible to reveal unknown HTs by monitoring suspicious behaviours and features.…”

Section: Future Directionsmentioning

confidence: 99%

Ten years of hardware Trojans: a survey from the attacker's perspective

Xue

Liu

et al. 2020

IET Computers & Digital Techniques

Self Cite

View full text Add to dashboard Cite

In the last decade, hardware Trojan has emerged as a serious concern in integrated circuit (IC) industry. As such, hardware Trojan detection techniques have been studied extensively. However, in order to develop reliable and effective defenses, it is important to figure out how hardware Trojans are implemented in practical scenarios. In this paper, we attempt to make a review of the hardware Trojan design and implementations in the last decade and also provide an outlook. Unlike all previous surveys that discuss Trojans from the defender's perspective, for the first time, we study the Trojans from the attacker's perspective, focusing on the attacker's methods, capabilities and challenges when he designs and implements a hardware Trojan. Particularly, the following questions are explored. What are the current methods and capabilities of attackers after ten years of research and development? By considering more and more sophisticated hardware Trojan detection techniques, what challenges do the attackers face, and vice versa? First, we present adversarial models in terms of the adversary's methods, adversary's capabilities and adversary's challenges in seven practical hardware Trojan implementation scenarios: in-house design team attacks, third-party intellectual property (3PIP) vendor attacks, computer-aided design (CAD) tools attacks, fabrication stage attacks, testing stage attacks, distribution stage attacks, and field programmable gate array (FPGA) Trojan attacks. Second, we analyze the hardware Trojan implementation methods under each adversarial model in terms of seven aspects/metrics: hardware Trojan attack scenarios, the attacker's motivation, feasibility (the practicality of the attacks), detectability (anti-detection capability of that kind of Trojan), protection and prevention suggestions for the designer, overhead analysis, and case studies of Trojan implementations. Finally, future directions on hardware Trojan attacks and defenses are discussed. This paper also presents several new insights and assumptions for the first time, including considering the Trojans not only from the copyright owner's perspective, but also from the users' perspective, and discussing the hardware Trojan attacks in the testing phase and in the distribution phase. This paper can hopefully provide a reference for future works on building effective hardware Trojan defenses.

show abstract

SC-COTD: Hardware Trojan Detection Based on Sequential/Combinational Testability Features using Ensemble Classifier

2021

View full text Add to dashboard Cite

Security against Hardware Trojans (HT) is an important concern in integrated circuits (IC) design and fabrication. Most of the current HT detection methods are based on the golden model of circuit design. Further, some approaches require test pattern for HTs activation. In this paper, we propose SC-COTD (Sequential/Combinational Controllability and Observability features for hardware Trojan Detection), an effective hardware Trojan detection to get rid of both golden chip and test pattern limitations. SC-COTD uses both sequential and combinational testability measures to detect and locate HT signals by a machine learning approach. This method deploys an ensemble classifier based on k-means clustering. The clustering models have diverse variety in testability features along with size of clustering which inspect and reveal different aspects of netlist conventional for a collaborative scheme. The clustering results are filtered and then fed into a decision-making procedure based on majority voting to eliminate the limited flaws of each model. The evaluation results on TrustHUB benchmarks demonstrate that, SC-COTD can detect and locate HTs with 100% without any false negative, i.e., Recall = 1. Although our method has a limited number of false positive, it has the best performance in comparison to well-known previous approaches.

show abstract

A Novel Golden Models-Free Hardware Trojan Detection Technique Using Unsupervised Clustering Analysis

Cited by 8 publications

References 15 publications

Defeating Untrustworthy Testing Parties: A Novel Hybrid Clustering Ensemble Based Golden Models-Free Hardware Trojan Detection Method

Defeating Untrustworthy Testing Parties: A Novel Hybrid Clustering Ensemble Based Golden Models-Free Hardware Trojan Detection Method

Ten years of hardware Trojans: a survey from the attacker's perspective

SC-COTD: Hardware Trojan Detection Based on Sequential/Combinational Testability Features using Ensemble Classifier

Contact Info

Product

Resources

About