Detection technique for hardware Trojans using machine learning in frequency domain

Iwase, Takato; Nozaki, Yusuke; Yoshikawa, Masayuki; Kumaki, Takeshi

doi:10.1109/gcce.2015.7398569

Cited by 50 publications

(15 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, Liu et al presented a combined PCA and SVM approach (i.e., PCA+SVM) to detect the covert communication-type Trojans by utilizing the transmission power waveform [73]. Iwase et al suggested converting the power waveform data from the time domain to the frequency domain through a discrete Fourier transform (DFT) and then conducting HT detection using SVM [87]. The PCA+SVM and DFT+SVM methods first preprocess the sample features and extract the effective part, which is more conducive to detecting and classifying HT instances.…”

Section: -Reverse Engineeringmentioning

confidence: 99%

“…In addition to PCA, there are several other pretreatment techniques that have been applied to side-channel features, e.g., wavelet translation [67], 2DPCA [71], and DFT [87] (see Table 15). Moreover, Xue et al introduced a modified unsupervised correlation-based feature selection method (UCFS) and adopted it to preprocess the raw power traces of ICs [91].…”

Section: ) Dimensionality Reduction and Pretreatmentmentioning

confidence: 99%

“…Note that the size of the training and testing datasets varies greatly in the literature. For example, the size of the training dataset exploited in [68] and [87] could be as small as 1 instance, while the size of the testing dataset utilized in [84] was as large as 500K samples (see Table 15).…”

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

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: ) Dimensionality Reduction and Pretreatmentmentioning

confidence: 99%

See 1 more Smart Citation

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

“…To detect hardware Trojan, several side-channel signals, such as power [64,65], timing [66,67], and spatial temperature [68], have been suggested. The existence of a Trojan in an IoT object or a circuit has some impacts on its components, the most common of which are on power and gates.…”

Section: Hardware Trojan Detectionmentioning

confidence: 99%

A Comprehensive Study of Security and Privacy Guidelines, Threats, and Countermeasures: An IoT Perspective

Abdulghani

Konstantas

2019

JSAN

View full text Add to dashboard Cite

As Internet of Things (IoT) involvement increases in our daily lives, several security and privacy concerns like linkability, unauthorized conversations, and side-channel attacks are raised. If they are left untouched, such issues may threaten the existence of IoT. They derive from two main reasons. One is that IoT objects are equipped with limited capabilities in terms of computation power, memory, and bandwidth which hamper the direct implementation of traditional Internet security techniques. The other reason is the absence of widely-accepted IoT security and privacy guidelines and their appropriate implementation techniques. Such guidelines and techniques would greatly assist IoT stakeholders like developers and manufacturers, paving the road for building secure IoT systems from the start and, thus, reinforcing IoT security and privacy by design. In order to contribute to such objective, we first briefly discuss the primary IoT security goals and recognize IoT stakeholders. Second, we propose a comprehensive list of IoT security and privacy guidelines for the edge nodes and communication levels of IoT reference architecture. Furthermore, we point out the IoT stakeholders such as customers and manufacturers who will benefit most from these guidelines. Moreover, we identify a set of implementation techniques by which such guidelines can be accomplished, and possible attacks against previously-mentioned levels can be alleviated. Third, we discuss the challenges of IoT security and privacy guidelines, and we briefly discuss digital rights management in IoT. Finally, through this survey, we suggest several open issues that require further investigation in the future. To the best of the authors’ knowledge, this work is the first survey that covers the above-mentioned objectives.

show abstract

“…The associate editor coordinating the review of this manuscript and approving it for publication was Remigiusz Wisniewski. with high efficiency in detecting the large and medium scale Trojans in FPGAs by analyzing their side channel information, e.g., Iwase et al [5] isolate the chip power signature to detect HT in the Trojan-infected FPGAs by using SVM (Support Vector Machine). The other refers to design file analyzing method which can isolate the Trojan-infected FPGAs by analyzing the characteristics of their netlist or RTL code.…”

Section: One Is Based On Physical Information Analyzing Which Ismentioning

confidence: 99%

A Comprehensive FPGA Reverse Engineering Tool-Chain: From Bitstream to RTL Code

et al. 2019

View full text Add to dashboard Cite

As recently studied, field-programmable gate arrays (FPGAs) suffer from growing Hardware Trojan (HT) attacks, and many techniques, e.g., register-transfer level (RTL) code-based analyzing, have been presented to detect HTs on FPGAs. However, for most of the FPGA end users, they can only obtain bitstream, rather than the RTL code. Therefore, we present a new FPGA reverse engineering tool-chain. It can precisely transform the FPGA bitstream to an RTL code and therefore assists in HT detection. In detail, we first construct an integrated database involving the FPGA architecture information and the bitstream mapping information. Then, we build two tools, namely, bitstream reversal tool (BRT) and netlist reversal tool (NRT). They can be combined together to retrieve the RTL code from the FPGA bitstream in moderate time. To demonstrate the effectiveness of our tool-chain, we evaluate it qualitatively and quantitatively by using two benchmarks (ISCAS'85 and ISCAS'89) and three real applications (8051 core, 68HC08, and AES). Our tool-chain is comprehensive since it covers all the reverse engineering stages, from bitstream to netlist and from netlist to code, without any support from other tools. Moreover, it rebuilds the netlist with a 100% correct rate and retrieves RTL code, which is exactly, functionally equivalent to the original one for all our benchmarks. To the best of our knowledge, it is the first tool that can perform integrated, precise reverse engineering for FPGAs, paving the way for the netlist-/code-based HT detection. INDEX TERMS FPGA, reverse engineering, bitstream, hardware trojan.

show abstract

Detection technique for hardware Trojans using machine learning in frequency domain

Cited by 50 publications

References 4 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

A Comprehensive Study of Security and Privacy Guidelines, Threats, and Countermeasures: An IoT Perspective

A Comprehensive FPGA Reverse Engineering Tool-Chain: From Bitstream to RTL Code

Contact Info

Product

Resources

About