Litcius/Paper detail

Poisoning the (Data) Well in ML-Based CAD: A Case Study of Hiding Lithographic Hotspots

Kang Liu, Benjamin Tan, Ramesh Karri, Siddharth Garg

202029 citationsDOI

Abstract

Machine learning (ML) provides state-of-the-art performance in many parts of computer-aided design (CAD) flows. However, deep neural networks (DNNs) are susceptible to various adversarial attacks, including data poisoning to compromise training to insert backdoors. Sensitivity to training data integrity presents a security vulnerability, especially in light of malicious insiders who want to cause targeted neural network misbehavior. In this study, we explore this threat in lithographic hotspot detection via training data poisoning, where hotspots in a layout clip can be "hidden" at inference time by including a trigger shape in the input. We show that training data poisoning attacks are feasible and stealthy, demonstrating a backdoored neural network that performs normally on clean inputs but misbehaves on inputs when a backdoor trigger is present. Furthermore, our results raise some fundamental questions about the robustness of ML-based systems in CAD.

Topics & Concepts

Computer scienceBackdoorRobustness (evolution)CADHotspot (geology)Artificial neural networkTrojanTraining setDeep learningArtificial intelligenceMachine learningAdversarial machine learningInferenceComputer securityData miningEngineeringGeologyEngineering drawingGeneGeophysicsChemistryBiochemistryAdversarial Robustness in Machine LearningPhysical Unclonable Functions (PUFs) and Hardware SecurityIntegrated Circuits and Semiconductor Failure Analysis
Poisoning the (Data) Well in ML-Based CAD: A Case Study of Hiding Lithographic Hotspots | Litcius