Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching

2026-05-21

AI Summary

This work addresses critical security vulnerabilities in Trusted Execution Environment (TEE) applications—such as data leakage and code injection—caused by improper partitioning, for which automated repair mechanisms have been lacking. The paper introduces TEERepair, the first framework capable of automatically repairing TEE partitioning errors. It encodes security repair patterns using a domain-specific language (DSL) and leverages large language models (LLMs) to understand the semantics of underlying C code, thereby generating context-aware repair patches and automatically constructing validation test clients. This approach overcomes key challenges including semantic extraction difficulty, absence of development guidelines, and insufficient verification methods. Evaluated on the PartitioningE-Bench benchmark, TEERepair achieves an 87.6% repair success rate and has contributed five pull requests to real-world TEE projects, two of which have already been merged.

Abstract

Trusted Execution Environments (TEEs) provide hardware-based isolation to protect sensitive data and computations from potentially compromised operating systems (OS). However, TEE applications inevitably interact with the untrusted OS through SDK interfaces, and improper partitioning can introduce severe vulnerabilities such as data leakage and code injection. While prior work has proposed static analysis tools to detect such issues, automated repair remains largely unexplored. This problem is particularly challenging due to three TEE-specific factors: the lack of standardized secure development guidelines, the difficulty of extracting semantic information from low-level C code, and the absence of mature testing and validation methods. In this work, we present TEERepair, a framework for automatically repairing bad partitioning issues in TEE applications. Our approach tackles the above challenges by introducing a domain-specific language (DSL) to encode repair rules that express and capture common TEE security patterns, which are instantiated as patch templates with placeholders for context-specific variables. We then leverage large language models (LLMs) to reason about code semantics and synthesize context-aware patches, and further generate test clients to validate the repairs. We evaluate TEERepair on the TEE Partitioning Errors Benchmark (PartitioningE-Bench), achieving a significantly higher repair success rate of 87.6% compared to baselines. Furthermore, applying TEERepair to real-world TEE projects, we submitted 5 repair pull requests, 2 of which have been confirmed and merged by project maintainers.

Problem

• Trusted Execution Environment
• Partitioning Issues
• Automated Repair
• Security Vulnerabilities
• TEE Applications

Innovation

• TEE repair
• domain-specific language
• large language models
• automated patching
• secure partitioning