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

Kang Liu, Benjamin Tan, Ramesh Karri, Siddharth Garg

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationProceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020
EditorsGiorgio Di Natale, Cristiana Bolchini, Elena-Ioana Vatajelu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages306-309
Number of pages4
ISBN (Electronic)9783981926347
DOIs
StatePublished - Mar 2020
Event2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020 - Grenoble, France
Duration: Mar 9 2020Mar 13 2020

Publication series

NameProceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020

Conference

Conference2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020
CountryFrance
CityGrenoble
Period3/9/203/13/20

ASJC Scopus subject areas

  • Hardware and Architecture
  • Safety, Risk, Reliability and Quality
  • Modeling and Simulation
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Poisoning the (Data) Well in ML-Based CAD: A Case Study of Hiding Lithographic Hotspots'. Together they form a unique fingerprint.

  • Cite this

    Liu, K., Tan, B., Karri, R., & Garg, S. (2020). Poisoning the (Data) Well in ML-Based CAD: A Case Study of Hiding Lithographic Hotspots. In G. Di Natale, C. Bolchini, & E-I. Vatajelu (Eds.), Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020 (pp. 306-309). [9116489] (Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/DATE48585.2020.9116489