Oracle-less machine learning (ML) attacks have broken various logic locking schemes. Regular synthesis, which is tailored for area-power-delay optimization, yields netlists where key-gate localities are vulnerable to learning. Thus, we call for security-aware logic synthesis. We propose ALMOST, a framework for adversarial learning to mitigate oracle-less ML attacks via synthesis tuning. ALMOST uses a simulated-annealing-based synthesis recipe generator, employing adversarially trained models that can predict state-of-the-art attacks' accuracies over wide ranges of recipes and key-gate localities. Experiments on ISCAS benchmarks confirm the attacks' accuracies drops to around 50\% for ALMOST-synthesized circuits, all while not undermining design optimization.
@article{arxiv.2303.03372,
title = {ALMOST: Adversarial Learning to Mitigate Oracle-less ML Attacks via Synthesis Tuning},
author = {Animesh Basak Chowdhury and Lilas Alrahis and Luca Collini and Johann Knechtel and Ramesh Karri and Siddharth Garg and Ozgur Sinanoglu and Benjamin Tan},
journal= {arXiv preprint arXiv:2303.03372},
year = {2023}
}
Comments
Accepted at Design Automation Conference (DAC 2023)