HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation
This addresses the need for more reliable and consistent decompilation in security reverse engineering workflows, offering a practical solution without requiring fine-tuning.
The paper tackles the problem of LLMs ignoring program control flow graphs in binary decompilation, which leads to fragile output, by introducing HELIOS, a framework that uses hierarchical text representations and optional compiler feedback to improve decompilation. The result is a significant increase in compilability, from 45.0% to 85.2% for Gemini 2.0 and up to over 94% with feedback, and functional correctness improvements of up to 5.6 percentage points across multiple architectures.
Large language models (LLMs) have recently been applied to binary decompilation, yet they still treat code as plain text and ignore the graphs that govern program control flow. This limitation often yields syntactically fragile and logically inconsistent output, especially for optimized binaries. This paper presents \textsc{HELIOS}, a framework that reframes LLM-based decompilation as a structured reasoning task. \textsc{HELIOS} summarizes a binary's control flow and function calls into a hierarchical text representation that spells out basic blocks, their successors, and high-level patterns such as loops and conditionals. This representation is supplied to a general-purpose LLM, along with raw decompiler output, optionally combined with a compiler-in-the-loop that returns error messages when the generated code fails to build. On HumanEval-Decompile for \texttt{x86\_64}, \textsc{HELIOS} raises average object file compilability from 45.0\% to 85.2\% for Gemini~2.0 and from 71.4\% to 89.6\% for GPT-4.1~Mini. With compiler feedback, compilability exceeds 94\% and functional correctness improves by up to 5.6 percentage points over text-only prompting. Across six architectures drawn from x86, ARM, and MIPS, \textsc{HELIOS} reduces the spread in functional correctness while keeping syntactic correctness consistently high, all without fine-tuning. These properties make \textsc{HELIOS} a practical building block for reverse engineering workflows in security settings where analysts need recompilable, semantically faithful code across diverse hardware targets.