Improving attacks on round-reduced Speck32/64 using deep learning

DOI10.1007/978-3-030-26951-7_6OpenAlexW2969001071MaRDI QIDQ2304981

Aron Gohr

Publication date: 9 March 2020

Full work available at URL: https://doi.org/10.1007/978-3-030-26951-7_6

zbMATH Keywords

differential cryptanalysisdeep learningSpeck

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Cryptography (94A60)

Related Items (12)

Subsampling and knowledge distillation on adversarial examples: new techniques for deep learning based side channel evaluations ⋮ Differential-ML distinguisher: machine learning based generic extension for differential cryptanalysis ⋮ Computing expected differential probability of (truncated) differentials and expected linear potential of (multidimensional) linear hulls in SPN block ciphers ⋮ MILP based differential attack on round reduced WARP ⋮ NNBits: bit profiling with a deep learning ensemble based distinguisher ⋮ Efficient detection of high probability statistical properties of cryptosystems via surrogate differentiation ⋮ Modeling large S-box in MILP and a (related-key) differential attack on full round PIPO-64/128 ⋮ Enhancing differential-neural cryptanalysis ⋮ Panther: a sponge based lightweight authenticated encryption scheme ⋮ A deeper look at machine learning-based cryptanalysis ⋮ deep_speck ⋮ Improved differential-linear attack with application to round-reduced Speck32/64

Uses Software

• SIMON
• Keras
• Adam
• GitHub
• SPECK

This page was built for publication: Improving attacks on round-reduced Speck32/64 using deep learning