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.

中文翻译：

---

从深度学习的角度攻击拆分制造

将生产线前端 (FEOL) 和生产线后端 (BEOL) 部件委托给不同代工厂的集成电路拆分制造的概念是为了防止生产过剩、知识产权 (IP) 盗版、或攻击者在 FEOL 设施中有针对性地插入硬件木马。在这项工作中，我们通过将各种布局级布局和布线提示制定为基于矢量和图像的特征来挑战拆分制造的安全承诺。我们构建了一个复杂的深度神经网络，可以高精度地推断出缺失的 BEOL 连接。与公开可用的网络流攻击 [1] 相比，对于同一组 ISCAS-85 基准，我们在 M1 上分裂时达到 1.21 倍的准确度，在 M3 上分裂时达到 1.12 倍的准确度，运行时间不到 1%。