| Title | Deep Learning-Based Image Analysis Framework for Hardware Assurance of Digital Integrated Circuits |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Lin, T., Shi, Y., Shu, N., Cheng, D., Hong, X., Song, J., Gwee, B. H. |
| Conference Name | 2020 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA) |
| Date Published | July 2020 |
| Publisher | IEEE |
| ISBN Number | 978-1-7281-6169-3 |
| Keywords | Analytical models, Artificial Intelligence (AI), Collaboration, composability, Deep Learning, digital IC, digital ICs, digital integrated circuits, DL-based methods, electronic engineering computing, essential analysis steps, feature extraction, Hardware, Hardware Assurance, hardware information, hardware information examination and verification, Human Behavior, Image analysis, information assurance, Integrated circuit modeling, integrated circuits, learning (artificial intelligence), machine learning, Metrics, policy-based governance, pubcrawl, resilience, Resiliency, Scalability, Scanning Electron Microscope images, SEM images, semiautomated training data preparation methods, Task Analysis |
| Abstract | We propose an Artificial Intelligence (AI)/Deep Learning (DL)-based image analysis framework for hardware assurance of digital integrated circuits (ICs). Our aim is to examine and verify various hardware information from analyzing the Scanning Electron Microscope (SEM) images of an IC. In our proposed framework, we apply DL-based methods at all essential steps of the analysis. To the best of our knowledge, this is the first such framework that makes heavy use of DL-based methods at all essential analysis steps. Further, to reduce time and effort required in model re-training, we propose and demonstrate various automated or semi-automated training data preparation methods and demonstrate the effectiveness of using synthetic data to train a model. By applying our proposed framework to analyzing a set of SEM images of a large digital IC, we prove its efficacy. Our DL-based methods are fast, accurate, robust against noise, and can automate tasks that were previously performed mainly manually. Overall, we show that DL-based methods can largely increase the level of automation in hardware assurance of digital ICs and improve its accuracy. |
| URL | https://ieeexplore.ieee.org/document/9261081 |
| DOI | 10.1109/IPFA49335.2020.9261081 |
| Citation Key | lin_deep_2020 |
Deep Learning-Based Image Analysis Framework for Hardware Assurance of Digital Integrated Circuits