The Big Hack Explained

Mehta, Dhwani; Lu, Hangwei; Paradis, Olivia P.; Azhagan, M S Mukhil; Rahman, Mir Tanjidur; Iskander, Yousef; Chawla, P.; Tehranipoor, Mark; Asadizanjani, Navid

doi:10.1145/3401980

Cited by 56 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, [18] proposes a placement defect detection approach using genetic algorithms while [19] proposes an approach using SURF and conventional morphological operations. A comprehensive survey of old and new hardware defect detection approaches can be found in [1,4]. In such methods, "defects" are defined in reference to a golden, i.e., non-defective, sample.…”

Section: Related Workmentioning

confidence: 99%

“…Printed circuit boards (PCBs) are essential components of many contemporary electronic systems, ranging from private sector computers and cell phones to public sector military and medical equipment. Predominant developments in the outsourcing of PCB manufacturing make boards increasingly vulnerable on a global scale to malicious changes from external entities [1]. Attacks such as hardware Trojan insertions provide backdoor access to sensitive networks and compromise a nation's infrastructure, military capability, and civil safety.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Why Is Deep Learning Challenging for Printed Circuit Board (PCB) Component Recognition and How Can We Address It?

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this paper, we present the need for specialized artificial intelligence (AI) for counterfeit and defect detection of PCB components. Popular computer vision object detection techniques are not sufficient for such dense, low inter-class/high intra-class variation, and limited-data hardware assurance scenarios in which accuracy is paramount. Hence, we explored the limitations of existing object detection methodologies, such as region based convolutional neural networks (RCNNs) and single shot detectors (SSDs), and compared them with our proposed method, the electronic component localization and detection network (ECLAD-Net). The results indicate that, of the compared methods, ECLAD-Net demonstrated the highest performance, with a precision of 87.2% and a recall of 98.9%. Though ECLAD-Net demonstrated decent performance, there is still much progress and collaboration needed from the hardware assurance, computer vision, and deep learning communities for automated, accurate, and scalable PCB assurance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Why Is Deep Learning Challenging for Printed Circuit Board (PCB) Component Recognition and How Can We Address It?

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…To motivate the techniques’ application, consider how PCA boards are becoming increasingly complex and densely packed with small components, making the clean separation of foreground and background pixels increasingly challenging. Performing this accurately makes a big difference in the ability to automate the visual inspection of PCA boards and to facilitate counterfeit or security analyses [ 18 ]. By automating the segmentation of lesions from medical images, physicians will be able to detect abnormalities clearly and make more accurate diagnoses.…”

Section: Introductionmentioning

confidence: 99%

A Two-Stage Automatic Color Thresholding Technique

Shamna

Ellam²,

Grübl

et al. 2023

Sensors

View full text Add to dashboard Cite

Thresholding is a prerequisite for many computer vision algorithms. By suppressing the background in an image, one can remove unnecessary information and shift one’s focus to the object of inspection. We propose a two-stage histogram-based background suppression technique based on the chromaticity of the image pixels. The method is unsupervised, fully automated, and does not need any training or ground-truth data. The performance of the proposed method was evaluated using a printed circuit assembly (PCA) board dataset and the University of Waterloo skin cancer dataset. Accurately performing background suppression in PCA boards facilitates the inspection of digital images with small objects of interest, such as text or microcontrollers on a PCA board. The segmentation of skin cancer lesions will help doctors to automate skin cancer detection. The results showed a clear and robust background–foreground separation across various sample images under different camera or lighting conditions, which the naked implementation of existing state-of-the-art thresholding methods could not achieve.

show abstract

“…Dielectric breakdown, electrical short circuit, and impedance mismatch are defects that can cause device failure [16]. These failures can be a product of manufacturing error or malicious alterations [6,17], but research has shown that it can be prevented through physical inspection using X-ray CT to perform dimensional analysis [17]. This dimensional analysis can be performed algorithmically based upon image processing techniques such as template matching between similar layers in the volume to segment the device's layer stack-up.…”

mentioning

confidence: 99%

Q.U.A.I.N.T.P.E.A.X. QUantifying Algorithmically INTrinsic Properties of Electronic Assemblies via X-ray CT

True

Jessurun²,

Mehta³

et al. 2021

Microsc Microanal

Self Cite

View full text Add to dashboard Cite

Electronic assemblies such as printed circuit boards (PCBs) and integrated circuits (ICs) require precise fabrication and process control of the electrical and mechanical properties. Microelectronic fabrication is a combination of additive methods, such as deposition of metal layers [18]; or subtractive, such as etching or milling [19]. This stack of layers in PCB or IC design creates the connectivity required for each device to operate functionally within a range of design specifications such as electrical resistance or impedance. The non-destructive verification of final assembled devices has become widespread with access to highenergy metrology equipment, demand for trusted devices [13], and to mitigate the complex defect-prone multilayer designs in PCB ( >8 Layer Lay-up) and IC (2.5D & 3D). Volumetric tools such as X-ray Micro Computed Tomography CT and Nano CT [9] are used to analyze the internal features of PCBs [5] and ICs [10] non-destructively. The automated quantification of these internal structures requires highresolution data to provide enough spatial resolution throughout the sample's "sliced" volume. Each slice's resolution in the volume represents the spatial resolution of the X-ray scan collection. To quantify internal structures such as signal traces or via connections the internal feature must be processed to separate or segment individual components enabling automated dimensional analysis or material property characterization. As the miniaturization of device geometries and the density of components increases, the labor resources required for manual segmentation of layered volumetric data becomes impossible.

show abstract

The Big Hack Explained

Cited by 56 publications

References 23 publications

Why Is Deep Learning Challenging for Printed Circuit Board (PCB) Component Recognition and How Can We Address It?

Why Is Deep Learning Challenging for Printed Circuit Board (PCB) Component Recognition and How Can We Address It?

A Two-Stage Automatic Color Thresholding Technique

Q.U.A.I.N.T.P.E.A.X. QUantifying Algorithmically INTrinsic Properties of Electronic Assemblies via X-ray CT

Contact Info

Product

Resources

About