Paper 2021/555
Neural-Network-Based Modeling Attacks on XOR Arbiter PUFs Revisited
Abstract
By revisiting, improving, and extending recent neural-network based modeling attacks on XOR Arbiter PUFs from the literature, we show that XOR Arbiter PUFs, (XOR) Feed-Forward Arbiter PUFs, and Interpose PUFs can be attacked faster, up to larger security parameters, and with fewer challenge-response pairs than previously known both in simulation and in silicon data. To support our claim, we discuss the differences and similarities of recently proposed modeling attacks and offer a fair comparison of the performance of these attacks by implementing all of them using the popular machine learning framework Keras and comparing their performance against the well-studied Logistic Regression attack. Our findings show that neural-network-based modeling attacks have the potential to outperform traditional modeling attacks on PUFs and must hence become part of the standard toolbox for PUF security analysis; the code and discussion in this paper can serve as a basis for the extension of our results to PUF designs beyond the scope of this work.
Note: Added analysis of Feed-Forward Arbiter PUF and variants.
Metadata
- Available format(s)
-
PDF
- Category
- Foundations
- Publication info
- Preprint.
- Keywords
- Physical Unclonable Function Strong PUFs Machine Learning Modeling Attacks XOR Arbiter PUF
- Contact author(s)
- nwisiol @ gmail com
- History
- 2022-06-20: revised
- 2021-04-28: received
- See all versions
- Short URL
- https://ia.cr/2021/555
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2021/555,
author = {Nils Wisiol and Bipana Thapaliya and Khalid T. Mursi and Jean-Pierre Seifert and Yu Zhuang},
title = {Neural-Network-Based Modeling Attacks on XOR Arbiter PUFs Revisited},
howpublished = {Cryptology ePrint Archive, Paper 2021/555},
year = {2021},
note = {\url{https://eprint.iacr.org/2021/555}},
url = {https://eprint.iacr.org/2021/555}
}
