Abstract
AbstractIn CRYPTO’2019, Gohr firstly introduced deep learning into differential cryptanalysis. He successfully found 5/6/7/8-round neural differential distinguishers of Speck32/64 and mounted key recovery attacks against 11/12-round Speck32/64 with a variant of Bayesian optimization. In this paper, we make some improvements to Gohr’s framework and apply it to Simeck32/64. We also present some parameter tuning experience for running deep learning assisted key recovery attacks. As proof, we obtain 8/9/10-round neural differential distinguishers for Simeck32/64 and successfully recover the penultimate round and last round subkeys for 13/14/15-round Simeck32/64 with low data complexity and time complexity.KeywordsDeep learningNeural distinguisherKey recovery attackBlock cipherSimeck
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
