mlsanityData to 13 Oct 2026

The Dark Side: Security Concerns in Machine Learning for EDA

arXiv 2203.10597 ↗First posted 20 Mar 2022cs.CR cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

The growing IC complexity has led to a compelling need for design efficiency improvement through new electronic design automation (EDA) methodologies. In recent years, many unprecedented efficient EDA methods have been enabled by machine learning (ML) techniques. While ML demonstrates its great potential in circuit design, however, the dark side about security problems, is seldomly discussed. This paper gives a comprehensive and impartial summary of all security concerns we have observed in ML for EDA. Many of them are hidden or neglected by practitioners in this field. In this paper, we first provide our taxonomy to define four major types of security concerns, then we analyze different application scenarios and special properties in ML for EDA. After that, we present our detailed analysis of each security concern with experiments.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 21 of its 79 references that are in the map. First posted on arXiv 20 Mar 2022.

Builds on

21 of 79 references.

References · 21

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,336
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,991
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,379
  5. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  6. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  7. 2016Stealing Machine Learning Models via Prediction APIscited by 617
  8. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 420
  9. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  10. 2018Robustness via curvature regularization, and vice versacited by 174
  11. 2020GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learningcited by 89
  12. 2021Machine Learning for Electronic Design Automation: A Surveycited by 71
9 more
  1. 2019DRiLLS: Deep Reinforcement Learning for Logic Synthesiscited by 47
  2. 2018Developing Synthesis Flows Without Human Knowledgecited by 29
  3. 2019Pyramid: Machine Learning Framework to Estimate the Optimal Timing and Resource Usage of a High-Level Synthesis Designcited by 17
  4. 2020PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Networkcited by 16
  5. 2019BagNet: Berkeley Analog Generator with Layout Optimizer Boosted with Deep Neural Networkscited by 11
  6. 2020A general approach for identifying hierarchical symmetry constraints for analog circuit layoutcited by 9
  7. 2020Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimationcited by 8
  8. 2020FIST: A Feature-Importance Sampling and Tree-Based Method for Automatic Design Flow Parameter Tuningcited by 5
  9. 2020Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attackscited by 2

Built on by

Not cited yet.