Research map / Learning theory and algorithms / Combinatorial and search optimization
Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a unified framework and benchmarks for evaluating ML-enhanced CDCL SAT solvers on cryptographic SAT problems.
Problem
Machine learning integrated with CDCL SAT solvers for cryptanalysis (key recovery, distinguisher construction) lacks a unified evaluation framework, making comparisons hard.
Approach
Introduces a unified SAT formulation and benchmark suite for cryptographic problems so that ML-based solvers can be evaluated consistently against CDCL baselines.
Experimental setup
Builds on: CDCL
Closest papers by meaning
- Learning with Enumeration: Neural-Guided SAT Framework for Cryptographic Key Recovery (NeurIPS 2026 · similarity 0.92)
- Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation (NeurIPS 2024 · similarity 0.92)
- On Cryptographic Attacks Using Backdoors for SAT (AAAI 2018 · similarity 0.89)
- FourierSAT: A Fourier Expansion-Based Algebraic Framework for Solving Hybrid Boolean Constraints (AAAI 2020 · similarity 0.88)
- G2SAT: Learning to Generate SAT Formulas (NeurIPS 2019 · similarity 0.87)
- HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.