Researchers in the University of Florida’s Florida Institute for Cybersecurity Research (FICS) have developed a semiautomated system that could have identified in seconds the malicious chips reportedly inserted into computer systems by the Chinese government.
The FICS system uses optical scans, microscopy, x-ray tomography, and artificial intelligence to compare a printed circuit board and its chips and components with the intended design.
The system takes high-resolution images of the front and back of the circuit board, then machine learning algorithms go through the images, tracing the interconnects and identifying the components. X-ray tomography imagery is then applied to examine interconnects and components buried within the circuit board.
Finally, the system captures a series of two-dimensional images and automatically combines them to produce a layer-by-layer analysis that maps the interconnects and the chips and components they connect.
From IEEE Spectrum
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA