论文标题
偏置克星：鲁棒性基于DL基于DL的光刻热点探测器针对后门攻击
Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks
论文作者
论文摘要
深度学习（DL）在整个CAD工具流中提供了潜在的改进，这是一种有希望的应用是光刻热点检测。但是，DL技术已被证明特别容易受到推理和训练时间对抗性攻击的影响。最近的工作表明，一小部分恶意的物理设计人员可以在其训练阶段隐秘地“后门”一个基于DL的热点探测器，从而准确地对常规布局剪辑进行了分类，但预测热点含有特殊制作的触发形状的热点。我们提出了一种新颖的培训数据增强策略，以此作为对这种后门攻击的有力辩护。辩方通过消除训练数据中引入的故意偏见而起作用，但不需要了解哪些训练样本被中毒或后门触发的性质。我们的结果表明，防御可以将攻击成功率从84％降低到约0％。
Deep learning (DL) offers potential improvements throughout the CAD tool-flow, one promising application being lithographic hotspot detection. However, DL techniques have been shown to be especially vulnerable to inference and training time adversarial attacks. Recent work has demonstrated that a small fraction of malicious physical designers can stealthily "backdoor" a DL-based hotspot detector during its training phase such that it accurately classifies regular layout clips but predicts hotspots containing a specially crafted trigger shape as non-hotspots. We propose a novel training data augmentation strategy as a powerful defense against such backdooring attacks. The defense works by eliminating the intentional biases introduced in the training data but does not require knowledge of which training samples are poisoned or the nature of the backdoor trigger. Our results show that the defense can drastically reduce the attack success rate from 84% to ~0%.
