REFICS: Assimilating Data-Driven Paradigms Into Reverse Engineering and Hardware Assurance on Integrated Circuits

Abstract

Comprehensive hardware assurance approaches guaranteeing trust on Integrated Circuits (ICs) typically require the verification of the IC design layout and functionality through destructive Reverse Engineering (RE). It is a resource intensive process that will benefit greatly from the extensive integration of data-driven paradigms, especially in the imaging and image analysis phase. Although obvious, this uptake of data-driven approaches into RE-assisted hardware assurance is lagging due to the lack of massive amounts of high-quality labelled data. In this paper, a large-scale synthetic Scanning Electron Microscopy (SEM) dataset, REFICS, is introduced to address this issue. The dataset, the first open-source dataset in the RE community, consists of 800,000 SEM images over two node technologies, 32nm and 90nm, and four cardinal layers of the IC, namely, doping, polysilicon, contact and metal layers. Furthermore, a framework, based on uncertainty and risk, is introduced to compare the efficacy and benefits of existing RE workflows utilizing ad-hoc steps in its execution. These developments are critical in developing RE-assisted hardware assurance into a scalable, automated and fault-tolerant approach. Finally, the work is concluded with the performance analysis of existing machine learning and deep learning approaches for image analysis in RE and hardware assurance.

Large‐scale time‐lapse scanning electron microscopy image mosaic using a smooth stitching strategy

“…Therefore, full image reconstruction by sequential image tiles containing local topographic information draws intense research interest in cases where the required inspection area exceeds the maximum imaging area (Rong et al, 2009; Zukić et al, 2021). Image stitching provides a global appearance of the sample, which facilitates the analysis of the full pattern and affects the subsequent quality evaluation of the product (Ma et al, 2007; Wilson et al, 2021). Stitching is also meaningful in other application fields, including the analysis of biological tissues (Rankov et al, 2005).…”

“…The different layers need to be aligned precisely for 3D reconstruction. For such inspections, SEM‐based overlay has been developed, which integrates high‐precision slicing as well as high‐resolution layer‐by‐layer imaging (Wilson et al, 2021). As a result, it is crucial to obtain large‐scale, high‐resolution, and high‐precision images of the full single‐layer structure by image stitching first.…”

SECURE: A Segmentation Quality Evaluation Metric on SEM Images for Reverse Engineering on Integrated Circuits

“…The necessity for this step stems from the introduction of artifacts during the layout extraction process. A detailed description of the artifacts and their sources were discussed in an earlier work [14]. A recent case study suggested that the time required for debugging the acquired data is much greater than the time frame required to image the entire IC [15].…”

A Tabletop X-Ray Tomography Instrument for Nanometer-Scale Imaging: Reconstructions

“…A manufacturer may be interested in process control, particularly in the case of new processes in the research and development phase. In a world in which the design and manufacture of chips are sometimes conducted by different organizations spanning the globe, there is a need to verify the design or detect counterfeit designs [2][3][4] . Reverse engineering is an additional motivation 1 .…”