A team of researchers at UF Warren B. Nelms Institute for the Connected World were awarded Top Picks in Hardware and Embedded Security 2021 by IEEE Hardware Security and Trust Technical Committee (HSTTC) for their work “SAIL: Machine Learning Guided Structural Analysis Attack on Hardware Obfuscation.’’ The research team includes Electrical and Computer Engineering (ECE) PhD students Prabuddha Chakraborty and Jonathan Cruz; UF alumnus Dr. Abdulrahman Alaql (PhD ’20, ECE), and Dr. Swarup Bhunia, Professor in ECE and Director of the Nelms Institute.
SAIL is an obfuscation evaluation tool written in C and Python which uses machine learning to recover the design intent of a gate-level design that has been logic locked. SAIL can identify structural signatures created by the interaction between combinational logic locking and logic synthesis which can be used to retrieve the locked design before synthesis. An attacker can use this information to gain knowledge of a design’s intent as well as more easily perform attacks such as removal of obfuscation gates or key guess attacks.
Top Picks in Hardware and Embedded Security is awarded to some of the best and high impact recently published works in the area of hardware and embedded security. The works are selected from conference papers that have been published during the last six years.
“We would like to thank IEEE HSTTC for this prestigious recognition. We are glad to see the impact of our work on the direction of structural obfuscation in the research community,” said Chakraborty and Cruz.
More information on their research can be found at https://cadforassurance.org/tools/evaluation-of-obfuscation/sail/