Paper 2023/819

NNBits: Bit Profiling with a Deep Learning Ensemble Based Distinguisher

Anna Hambitzer, Technology Innovation Institute
David Gerault, Technology Innovation Institute
Yun Ju Huang, Technology Innovation Institute
Najwa Aaraj, Technology Innovation Institute
Emanuele Bellini, Technology Innovation Institute
Abstract

We introduce a deep learning ensemble (NNBits) as a tool for bit-profiling and evaluation of cryptographic (pseudo) random bit sequences. Onthe one hand, we show how to use NNBits ensemble to ex-plain parts of the seminal work of Gohr [16]: Gohr’s depth-1 neural distinguisher reaches a test accuracy of 78.3% in round 6 for SPECK32/64 [3]. Using the bit-level information provided by NNBits we can partially ex- plain the accuracy obtained by Gohr (78.1% vs. 78.3%). This is achieved by constructing a distinguisher which only uses the information about correct or incorrect predictions on the single bit level and which achieves 78.1% accuracy. We also generalize two heuristic aspects in the construction of Gohr’s network: i) the particular input structure, which reflects expert knowledge of SPECK32/64, as well as ii) the cyclic learning rate. On the other hand, we extend Gohr’s work as a statistical test on avalanche datasets of SPECK32/64, SPECK64/128, SPECK96/144, SPECK128/128, and AES-128. In combination with NNBits ensemble we use the extended version of Gohr’s neural network to draw a comparison with the NIST Statistical Test Suite (NIST STS) on the previously mentioned avalanche datasets. We compare NNBits in conjunction with Gohr’s generalized network to the NIST STS and conclude that the NNBits ensemble performs either as good as the NIST STS or better. Furthermore, we demonstrate cryptanalytic insights that result from bit-level profiling with NNBits, for example, we show how to infer the strong input difference (0x0040, 0x0000) for SPECK32/64 or infer a signature of the multiplication in the Galois field of AES-128.

Metadata
Available format(s)
PDF
Category
Attacks and cryptanalysis
Publication info
Published elsewhere. RSA-CT
DOI
10.1007/978-3-031-30872-7_19
Keywords
Evaluation toolsBlock cipherDistinguisherAvalanche datasetBit-profilingNeural networksRandom number generator
Contact author(s)
anna hambitzer @ tii ae
David Gerault @ tii ae
Yunju Huang @ tii ae
Najwa Aaraj @ tii ae
Emanuele Bellini @ tii ae
History
2023-06-06: approved
2023-06-02: received
See all versions
Short URL
https://ia.cr/2023/819
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2023/819,
      author = {Anna Hambitzer and David Gerault and Yun Ju Huang and Najwa Aaraj and Emanuele Bellini},
      title = {{NNBits}: Bit Profiling with a Deep Learning Ensemble Based Distinguisher},
      howpublished = {Cryptology {ePrint} Archive, Paper 2023/819},
      year = {2023},
      doi = {10.1007/978-3-031-30872-7_19},
      url = {https://eprint.iacr.org/2023/819}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.