Hardware Trojan Detection Based on Cluster Analysis of Mahalanobis Distance

Cui, Qi; Sun, Kewang; Wang, Sixiang; Zhang, Lei; Li, Dongxu

doi:10.1109/ihmsc.2016.65

Cited by 9 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Otherwise, 2DPCA can be performed to address the high-dimensional power maps converted from thermal radiation data; then DBSCAN can be exploited to detect and locate the HTs. Cui et al developed an HT detection method with the Markov distance as the clustering center [90]. The collected power-consumption is first analyzed by PCA, and then, the clustering operation is completed with the Mahalanobis distance as the class center.…”

Section: -Reverse Engineeringmentioning

confidence: 99%

“…This procedure can offset the requirements for golden ICs and utilize simulation-based data to represent them; however, this technique still needs golden designs as a reference. Moreover, researchers have attempted to exploit CAs to build trusted reference libraries to shift the demands for trusted ICs [71], [90], [91]. However, all the aforementioned approaches are still in the experimental simulation stage, and there is still a long way to go before practical applications are realized.…”

Section: -Implantation Preventionmentioning

confidence: 99%

“…PCA is an effective dimensionality reduction method and is mostly utilized to address circuit parameter-related features (see Tables 15 -16). For instance, Cui et al employed the PCA method to reduce the original 10000-dimensional power data to 2050 dimensions, thus greatly reducing the amount of computations [90]. In [104], after using PCA to reduce the number of data dimensions from 8000 to 17, the structure of the NN was decreased from 8000×89×1 to 17×5×1, which increased the HT detection accuracy from 41% to 100% and reduced the computational complexity of the NN by more than 8000 times.…”

Section: ) Dimensionality Reduction and Pretreatmentmentioning

confidence: 99%

“…Note that in addition to Markv distance-based CA, unsupervised learning models only require testing datasets as input such as in [70], [85], [91], [111], and [114] (see Tables 15 -18). Some researchers use sample datasets with labels as unlabeled data, for example, the work of Cui et al in [90], to train the learning models and then validate them using the testing datasets.…”

Section: ) Effect Of the Training And Testing Dataset Sizesmentioning

confidence: 99%

See 3 more Smart Citations

A Survey on Machine Learning Against Hardware Trojan Attacks: Recent Advances and Challenges

et al. 2020

View full text Add to dashboard Cite

The remarkable success of machine learning (ML) in a variety of research domains has inspired academic and industrial communities to explore its potential to address hardware Trojan (HT) attacks. While numerous works have been published over the past decade, few survey papers, to the best of our knowledge, have systematically reviewed the achievements and analyzed the remaining challenges in this area. To fill this gap, this article surveys ML-based approaches against HT attacks available in the literature. In particular, we first provide a classification of all possible HT attacks and then review recent developments from four perspectives, i.e., HT detection, design-for-security (DFS), bus security, and secure architecture. Based on the review, we further discuss the lessons learned in and challenges arising from previous studies. Despite current work focusing more on chip-layer HT problems, it is notable that novel HT threats are constantly emerging and have evolved beyond chips and to the component, device, and even behavior layers, therein compromising the security and trustworthiness of the overall hardware ecosystem. Therefore, we divide the HT threats into four layers and propose a hardware Trojan defense (HTD) reference model from the perspective of the overall hardware ecosystem, therein categorizing the security threats and requirements in each layer to provide a guideline for future research in this direction.

show abstract

Section: -Reverse Engineeringmentioning

confidence: 99%

Section: -Implantation Preventionmentioning

confidence: 99%

Section: ) Dimensionality Reduction and Pretreatmentmentioning

confidence: 99%

Section: ) Effect Of the Training And Testing Dataset Sizesmentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Machine Learning Against Hardware Trojan Attacks: Recent Advances and Challenges

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In 2007, D. Agrawal et al proposed the side-channel signal analysis detection method by using power, temperature and electromagnetic profiles to reflect HT effects [11]. Improving the detection precision by changing the profiles process algorithm [12,13,14,15,16,17,18,19]. In 2011, Zhang proposed an on-chip Ring Oscillator Network (RON) for HT detection as a trusted hardware design.…”

Section: Introductionmentioning

confidence: 99%

Fault attack hardware Trojan detection method based on ring oscillator

Fang

et al. 2019

IEICE Electron. Express

View full text Add to dashboard Cite

Recently proposed common hardware Trojan detection methods can detect wide range of Trojan types, however, there is no explicit detection method for specific Trojan types. These types of Trojan lead to low detection efficiency due to variety of categories and complex features. Keeping in view the special characteristics of Fault Attack Hardware Trojan (FAHT), a method for detection of FAHT is proposed in this letter. Proposed methodology uses ring Oscillator detection circuit that can detect extra logic gate on original cipher circuit where each byte is not required to be injected into the circuit. The experiments show that when the Trojan circuit of area 0.0495% is implanted into the original AES circuit, the detection method in this paper can detect them successfully. In addition, the proposed detection approach has high flexibility to implement in other cipher circuit.

show abstract

Machine Learning–Based Hardware Trojans Detection in Integrated Circuits: A Systematic Review

Sharma,

Ranjan

2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Hardware Trojan Detection Based on Cluster Analysis of Mahalanobis Distance

Cited by 9 publications

References 6 publications

A Survey on Machine Learning Against Hardware Trojan Attacks: Recent Advances and Challenges

A Survey on Machine Learning Against Hardware Trojan Attacks: Recent Advances and Challenges

Fault attack hardware Trojan detection method based on ring oscillator

Machine Learning–Based Hardware Trojans Detection in Integrated Circuits: A Systematic Review

Contact Info

Product

Resources

About