Attacking Split Manufacturing from a Deep Learning Perspective
This work challenges the security of split manufacturing, which is crucial for preventing IP piracy and hardware Trojans in semiconductor design.
The paper tackled the security of split manufacturing in integrated circuits by using deep learning to infer missing connections, achieving 1.21X and 1.12X higher accuracy than prior attacks with less than 1% running time.
The notion of integrated circuit split manufacturing which delegates the front-end-of-line (FEOL) and back-end-of-line (BEOL) parts to different foundries, is to prevent overproduction, piracy of the intellectual property (IP), or targeted insertion of hardware Trojans by adversaries in the FEOL facility. In this work, we challenge the security promise of split manufacturing by formulating various layout-level placement and routing hints as vector- and image-based features. We construct a sophisticated deep neural network which can infer the missing BEOL connections with high accuracy. Compared with the publicly available network-flow attack [1], for the same set of ISCAS-85 benchmarks, we achieve 1.21X accuracy when splitting on M1 and 1.12X accuracy when splitting on M3 with less than 1% running time.