ModelForge: Using GenAI to Improve the Development of Security Protocols

2025-06-08

AI Summary

Manual translation of natural-language protocol specifications into formal models (e.g., CPSA) is complex and inefficient, severely hindering the practical adoption of formal verification. This paper introduces the first generative AI (GenAI) framework tailored for security protocol modeling, enabling end-to-end automated translation from natural-language specifications to executable CPSA models. Our approach integrates fine-tuned large language models (LLMs), CPSA syntactic constraints, and protocol semantic parsing to ensure both syntactic correctness and semantic fidelity of generated models. Experimental evaluation demonstrates that our system achieves the highest syntactic accuracy among competing models, consistently produces runnable CPSA specifications, and significantly reduces modeling time. While minor details still require human validation, the framework substantially lowers the barrier to adopting formal methods. The core contribution is the design and open-sourcing of the first GenAI toolchain dedicated to protocol formalization, accompanied by a verifiable prototype implementation.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Security and Privacy: Large-scale security measurements

Abstract

Formal methods can be used for verifying security protocols, but their adoption can be hindered by the complexity of translating natural language protocol specifications into formal representations. In this paper, we introduce ModelForge, a novel tool that automates the translation of protocol specifications for the Cryptographic Protocol Shapes Analyzer (CPSA). By leveraging advances in Natural Language Processing (NLP) and Generative AI (GenAI), ModelForge processes protocol specifications and generates a CPSA protocol definition. This approach reduces the manual effort required, making formal analysis more accessible. We evaluate ModelForge by fine-tuning a large language model (LLM) to generate protocol definitions for CPSA, comparing its performance with other popular LLMs. The results from our evaluation show that ModelForge consistently produces quality outputs, excelling in syntactic accuracy, though some refinement is needed to handle certain protocol details. The contributions of this work include the architecture and proof of concept for a translating tool designed to simplify the adoption of formal methods in the development of security protocols.

Problem

• Automates translation of security protocols into formal representations
• Reduces manual effort in formal analysis of protocols
• Improves accessibility of formal methods for protocol development

Innovation

• Automates translation of protocol specifications
• Leverages NLP and GenAI for processing
• Fine-tunes LLM for CPSA protocol generation