# The Dark Side: Security Concerns in Machine Learning for EDA

arXiv: https://arxiv.org/abs/2203.10597 · HTML: https://mlsanity.com/paper/2203.10597/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 79 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning](https://mlsanity.com/paper/1702.07464/) (2017)
- [Robustness via curvature regularization, and vice versa](https://mlsanity.com/paper/1811.09716/) (2018)
- [GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning](https://mlsanity.com/paper/2005.00406/) (2020)
- [Machine Learning for Electronic Design Automation: A Survey](https://mlsanity.com/paper/2102.03357/) (2021)
- [DRiLLS: Deep Reinforcement Learning for Logic Synthesis](https://mlsanity.com/paper/1911.04021/) (2019)
- [Developing Synthesis Flows Without Human Knowledge](https://mlsanity.com/paper/1804.05714/) (2018)
- [Pyramid: Machine Learning Framework to Estimate the Optimal Timing and Resource Usage of a High-Level Synthesis Design](https://mlsanity.com/paper/1907.12952/) (2019)
- [PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Network](https://mlsanity.com/paper/2011.13494/) (2020)
- [BagNet: Berkeley Analog Generator with Layout Optimizer Boosted with Deep Neural Networks](https://mlsanity.com/paper/1907.10515/) (2019)
- [A general approach for identifying hierarchical symmetry constraints for analog circuit layout](https://mlsanity.com/paper/2010.00051/) (2020)
- [Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimation](https://mlsanity.com/paper/2011.13522/) (2020)
- [FIST: A Feature-Importance Sampling and Tree-Based Method for Automatic Design Flow Parameter Tuning](https://mlsanity.com/paper/2011.13493/) (2020)
- [Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks](https://mlsanity.com/paper/2004.12492/) (2020)

## 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.