Context-Guided Decompilation: A Step Towards Re-executability

TL;DR

This paper introduces ICL4Decomp, a hybrid framework using in-context learning to improve the re-executability of decompiled binaries, addressing limitations of existing neural decompilation methods.

Contribution

The paper presents a novel ICL-based approach that significantly enhances the re-executability of decompiled code from optimized binaries.

Findings

Approximately 40% improvement in re-executability over existing methods

Robustness maintained across multiple datasets and compiler optimizations

Addresses semantic loss issues in neural decompilation

Abstract

Binary decompilation plays an important role in software security analysis, reverse engineering, and malware understanding when source code is unavailable. However, existing decompilation techniques often fail to produce source code that can be successfully recompiled and re-executed, particularly for optimized binaries. Recent advances in large language models (LLMs) have enabled neural approaches to decompilation, but the generated code is typically only semantically plausible rather than truly executable, limiting their practical reliability. These shortcomings arise from compiler optimizations and the loss of semantic cues in compiled code, which LLMs struggle to recover without contextual guidance. To address this challenge, we propose ICL4Decomp, a hybrid decompilation framework that leverages in-context learning (ICL) to guide LLMs toward generating re-executable source code. We evaluate our method across multiple datasets, optimization levels, and compilers, demonstrating around 40\% improvement in re-executability over state-of-the-art decompilation methods while maintaining robustness.