An AI Approach to Verified Production Cryptographic Libraries
cs.CR, cs.AI
Submitted: 2026-08-02
Updated: 2026-10-16
Code: https://github.com/ChuyueSun/CryptoProver
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AutoVerus: Automated Proof Generation for Rust Code
- Towards Repository-Level Program Verification with Large Language Models
- KVerus: Scalable and Resilient Formal Verification Proof Generation for Rust Code
- VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus
- Verus: Verifying Rust Programs using Linear Ghost Types (extended version)
- VeruSAGE: A Study of Agent-Based Verification for Rust Systems
- Lost in the Middle: How Language Models Use Long Contexts
- Clover: Closed-Loop Verifiable Code Generation
- VERINA: Benchmarking Verifiable Code Generation
- Lemur: Integrating Large Language Models in Automated Program Verification
- Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
- Verified Correctness and Security of mbedTLS HMAC-DRBG
- The Last Mile: High-Assurance and High-Speed Cryptographic Implementations
- CryptOpt: Verified Compilation with Randomized Program Search for Cryptographic Primitives (full version)
- A Rust-to-Lean Verification Pipeline with AI Provers: An Experience Report
- Automating Formal Verification with Reinforcement Learning and Recursive Inference
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
- AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
- A benchmark for vericoding: formally verified program synthesis
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills