CAD for Assurance of Electronic Systems
 

A Computationally Efficient Tensor Regression Network based Modeling Attack on XOR Arbiter PUF and its Variants

By: Pranesh Santikellur (IIT Kharagpur) and Rajat Subhra Chakraborty (IIT Kharagpur)

Stage: Attack tool

Summary

XOR Arbiter PUF (XOR APUF) have proven to be more robust to machine learning based modeling attacks.This tool implements tensor regression based modeling attack on XOR Arbiter PUF. Tensor regression model uses a variant of CANDECOMP/PARAFAC decomposition technique to reduce the computational resource requirement of model building attacks on XOR APUF.

Contact

Pranesh Santikellur

Input/Output Interface

  • Input: python ecp_trn_7xor.py
  • Output: validation Accuracy

Dependencies

Python 2.7; Tensorflow 1.13

Licensing Info

Open-source

References

Santikellur, Pranesh; Chakraborty, Rajat Subhra

A Computationally Efficient Tensor Regression Network based Modeling Attack on XOR Arbiter PUF and its Variants Journal Article

In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, pp. 1-1, 2020, ISSN: 1937-4151.

Abstract | Links | BibTeX

Acknowledgments

  • Intel Corporation

User Guide Link can be found at this link