AI-Powered Terahertz VLSI Testing Technology for Ensuring Hardware Security and Reliability

Akter, Naznin; Siddiquee, Masudur R.; Shur, M. S.; Pala, Nezih

doi:10.1109/access.2021.3075429

Cited by 8 publications

(3 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The counterfeit IC is identified from the response signature of ICs by applying terahertz radiations to the pins in [51]. The DC voltages response obtained by injecting terahertz or sub-terahertz radiations at the IC Pins are used to measure the performance deviations and defects subject to reliability and process variations.…”

Section: Image Analysis Methodsmentioning

confidence: 99%

A review on machine learning based counterfeit integrated circuit detection

Udaya Shankar,

Kalpana

2023

Eng. Res. Express

View full text Add to dashboard Cite

Counterfeit electronics parts have changed today’s electronic market all over the world. A large number of Integrated Circuit (IC) designers, manufacturers and suppliers present in the market have led to an increase in the counterfeiting. Still, there are no proper standards are formulated to regulate the spread of counterfeit electronics. Large number of research solutions is provided to identify them. Still, several forms of counterfeit ICs are not yet detected up to an extent. One of the promising solutions developed in recent research is the use of machine learning algorithms in the detection of counterfeit ICs. A state-of-the-art survey on the electrical and physical inspection methods to detect the counterfeit ICs using various machine learning approaches with other algorithms are presented and compared. Future directions for the identification of counterfeit ICs are also provided to increase the lifetime of the circuit.

show abstract

Section: Image Analysis Methodsmentioning

confidence: 99%

A review on machine learning based counterfeit integrated circuit detection

Udaya Shankar,

Kalpana

2023

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…TeraFET technology will also enable THz applications including astronomical science [ 133 , 134 , 135 ], earth observation [ 136 ], sensing [ 137 , 138 , 139 ], chemical analysis [ 140 , 141 ], homeland security, concealed weapon and explosive detection [ 142 , 143 ], industrial controls [ 144 , 145 ], compact radars [ 146 , 147 ], structural integrity testing, spacecraft tiles control [ 144 ], Internet of Things (IoT), biotechnology [ 148 , 149 , 150 ], medicine [ 151 , 152 ], including cancer diagnostics [ 153 ], and non-destructive VLSI testing during the manufacturing process [ 154 ] and in-situ checking of the THz scans of chips [ 155 , 156 , 157 , 158 , 159 ]. Artificial intelligence processing of the VLSI THz scans allows distinguishing between genuine and fake VLSI for hardware cyber security applications [ 158 ]. Figure 11 shows the THz frequency ranges for different applications of the THz technology.…”

Section: Other Terafet Applicationsmentioning

confidence: 99%

Plasmonic Field-Effect Transistors (TeraFETs) for 6G Communications

Shur

Aǐzin

Otsuji

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Ever increasing demands of data traffic makes the transition to 6G communications in the 300 GHz band inevitable. Short-channel field-effect transistors (FETs) have demonstrated excellent potential for detection and generation of terahertz (THz) and sub-THz radiation. Such transistors (often referred to as TeraFETs) include short-channel silicon complementary metal oxide (CMOS). The ballistic and quasi-ballistic electron transport in the TeraFET channels determine the TeraFET response at the sub-THz and THz frequencies. TeraFET arrays could form plasmonic crystals with nanoscale unit cells smaller or comparable to the electron mean free path but with the overall dimensions comparable with the radiation wavelength. Such plasmonic crystals have a potential of supporting the transition to 6G communications. The oscillations of the electron density (plasma waves) in the FET channels determine the phase relations between the unit cells of a FET plasmonic crystal. Excited by the impinging radiation and rectified by the device nonlinearities, the plasma waves could detect both the radiation intensity and the phase enabling the line-of-sight terahertz (THz) detection, spectrometry, amplification, and generation for 6G communication.

show abstract

“…Their automated labeling network improved the labeling speed of THz waveforms tenfold compared to traditional methods, achieving a defect recognition accuracy of 99.28% and an F1 score of 99.73%, The proposed network solves the problems of the low efficiency of the defect identification method of adhesive structures and the considerable influence of subjective factors and promotes the development of THz non-destructive testing technology [16]. Currently, many scholars are exploring the application of CNNs and recurrent neural networks in THz time-domain spectroscopy (THz-TDS) recognition [17,18].…”

Section: Introductionmentioning

confidence: 99%

Quantitative Detection of Defects in Multi-Layer Lightweight Composite Structures Using THz-TDS Based on a U-Net-BiLSTM Network

Zhang,

Li,

Zhang

et al. 2024

Materials

View full text Add to dashboard Cite

Multi-layer lightweight composite structures are widely used in the field of aviation and aerospace during the processes of manufacturing and use, and, as such, they inevitably produce defects, damage, and other quality problems, creating the need for timely non-destructive testing procedures and the convenient repair or replacement of quality problems related to the material. When using terahertz non-destructive testing technology to detect defects in multi-layer lightweight composite materials, due to the complexity of their structure and defect types, there are many signal characteristics of terahertz waves propagating in the structures, and there is no obvious rule behind them, resulting in a large gap between the recognition results and the actual ones. In this study, we introduced a U-Net-BiLSTM network that combines the strengths of the U-Net and BiLSTM networks. The U-Net network extracts the spatial features of THz signals, while the BiLSTM network captures their temporal features. By optimizing the network structure and various parameters, we obtained a model tailored to THz spectroscopy data. This model was subsequently employed for the identification and quantitative analysis of defects in multi-layer lightweight composite structures using THz non-destructive testing. The proposed U-Net-BiLSTM network achieved an accuracy of 99.45% in typical defect identification, with a comprehensive F1 score of 99.43%, outperforming the CNN, ResNet, U-Net, and BiLSTM networks. By leveraging defect classification and thickness recognition, this study successfully reconstructed three-dimensional THz defect images, thereby realizing quantitative defect detection.

show abstract

AI-Powered Terahertz VLSI Testing Technology for Ensuring Hardware Security and Reliability

Cited by 8 publications

References 66 publications

A review on machine learning based counterfeit integrated circuit detection

A review on machine learning based counterfeit integrated circuit detection

Plasmonic Field-Effect Transistors (TeraFETs) for 6G Communications

Quantitative Detection of Defects in Multi-Layer Lightweight Composite Structures Using THz-TDS Based on a U-Net-BiLSTM Network

Contact Info

Product

Resources

About