Is ML-based cryptanalysis inherently limited? Simulating cryptographic adversaries via gradient-based methods

DOI10.1007/978-3-031-68391-6_2MaRDI QIDQ6652981zbMATH OpenFDO

Authors Avital Shafran, Eran Malach, Thomas Ristenpart, Gil Segev, Stefano Tessaro

Publication date 13 December 2024

Full work available at URL https://doi.org/10.1007/978-3-031-68391-6_2

Mathematics Subject Classification ID

Cryptography (94A60)

Cites work

• A deeper look at machine learning-based cryptanalysis
• A Stochastic Approximation Method
• A theory of the learnable
• BKZ 2.0: Better lattice security estimates
• Cryptographic hardness for learning intersections of halfspaces
• Cryptographic hardness of distribution-specific learning
• Differential-ML distinguisher: machine learning based generic extension for differential cryptanalysis
• ECC2K-130 on Cell CPUs
• ECC2K-130 on NVIDIA GPUs
• Efficient noise-tolerant learning from statistical queries
• FSBday
• scientific article; zbMATH DE number 3489106 (Why is no real title available?)
• scientific article; zbMATH DE number 697831 (Why is no real title available?)
• scientific article; zbMATH DE number 1942427 (Why is no real title available?)
• Improved Differential Cryptanalysis of Round-Reduced Speck
• Improving attacks on round-reduced Speck32/64 using deep learning
• Monte Carlo Methods for Index Computation (mod p)
• More insight on deep learning-aided cryptanalysis
• On lattices, learning with errors, random linear codes, and cryptography
• Parallel collision search with cryptanalytic applications
• Public-key cryptography from different assumptions
• Solving a 112-bit prime elliptic curve discrete logarithm problem on game consoles using sloppy reduction
• Understanding machine learning. From theory to algorithms

This page was built for publication: Is ML-based cryptanalysis inherently limited? Simulating cryptographic adversaries via gradient-based methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6652981)