AutoSOUP: Safety-Oriented Unit Proof Generation for Component-level Memory-Safety Verification

2026-05-11

AI Summary

Memory safety vulnerabilities are prevalent in low-level embedded software, yet existing verification approaches rely heavily on manual intervention, hindering their scalability. This work proposes a formal framework of Safety-Oriented Unit Proofs that leverages a hybrid architecture combining program synthesis and large language models (LLMs) to automatically generate interpretable verification artifacts. These artifacts precisely characterize the verification scope, loop bounds, and environmental assumptions. The approach enables automated, component-level memory safety verification, effectively uncovering vulnerabilities in multiple real-world components. Furthermore, it systematically formalizes the soundness conditions underpinning the generated proofs, significantly reducing reliance on expert knowledge.

Abstract

Memory-safety errors remain a persistent source of zero-day vulnerabilities in low-level software. The problem is especially acute in embedded systems, where hardware protections are often limited and dynamic analysis is difficult to apply effectively. Memory-safety verification can provide stronger assurance by proving the absence of such errors or exposing violations when they exist. However, current verification workflows remain largely manual and require substantial specialized expertise, limiting their adoption in practice. We present AutoSOUP, a system for automating component-level memory-safety verification through Safety-Oriented Unit Proofs. We formalize these unit proofs as artifacts that encode verification choices (scope, loop bounds, and environment models) for verifying safety properties, and introduce three techniques for deriving them automatically. To overcome the limitations of existing automation approaches, we further introduce LLM-As-Function-Call, a hybrid architecture that combines deterministic program synthesis with LLMs to automate these techniques and produce justifiable unit proofs. We evaluate AutoSOUP by assessing its ability to automate memory-safety verification and expose vulnerabilities in verified components, and we characterize the assumptions and guarantees of the resulting proofs.

Problem

• memory-safety verification
• component-level verification
• manual verification workflow
• embedded systems
• zero-day vulnerabilities

Innovation

• Safety-Oriented Unit Proofs
• Memory-Safety Verification
• Automated Program Verification
• LLM-As-Function-Call
• Component-level Verification