Reproduce “Confidence-Guided Protocol IR for LLM-Aided Security Protocol Modeling” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Siqi Li, Yufan Cai, Hongshu Wang, Xinyue Zuo, Zhe Hou, Jin Song Dong
The Protocol IR pipeline helps reviewers inspect and correct an LLM’s semantic model of a security protocol before generating SAPIC+ code for Tamarin. It exposes roles, messages, checks, proof targets, and assumptions, but does not guarantee faithful interpretation. In 18 cases, GPT-5.5 models were all accepted; 14 matched expected outcomes, a measure distinct from semantic fidelity.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.