SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin

• URL: http://arxiv.org/abs/2509.22114v1
• Date: Fri, 26 Sep 2025 09:35:46 GMT
• Title: SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin
• Authors: Hanzhuo Tan, Weihao Li, Xiaolong Tian, Siyi Wang, Jiaming Liu, Jing Li, Yuqun Zhang,
• Abstract summary: We introduce SK2Decompile, a novel two-phase approach to decompile from the skeleton (semantic structure) to the skin (identifier) of programs.<n>Specifically, we first apply a Structure Recovery model to translate a program's binary code to an Intermediate Representation (IR) as deriving the program's "skeleton"<n>We apply reinforcement learning to reward the model for producing program structures that adhere to the syntactic and semantic rules expected by compilers.
• Score: 17.843213826367343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have emerged as a promising approach for binary decompilation. However, the existing LLM-based decompilers still are somewhat limited in effectively presenting a program's source-level structure with its original identifiers. To mitigate this, we introduce SK2Decompile, a novel two-phase approach to decompile from the skeleton (semantic structure) to the skin (identifier) of programs. Specifically, we first apply a Structure Recovery model to translate a program's binary code to an Intermediate Representation (IR) as deriving the program's "skeleton", i.e., preserving control flow and data structures while obfuscating all identifiers with generic placeholders. We also apply reinforcement learning to reward the model for producing program structures that adhere to the syntactic and semantic rules expected by compilers. Second, we apply an Identifier Naming model to produce meaningful identifiers which reflect actual program semantics as deriving the program's "skin". We train the Identifier Naming model with a separate reinforcement learning objective that rewards the semantic similarity between its predictions and the reference code. Such a two-phase decompilation process facilitates advancing the correctness and readability of decompilation independently. Our evaluations indicate that SK2Decompile, significantly outperforms the SOTA baselines, achieving 21.6% average re-executability rate gain over GPT-5-mini on the HumanEval dataset and 29.4% average R2I improvement over Idioms on the GitHub2025 benchmark.

Related papers

• Cross-modal Retrieval Models for Stripped Binary Analysis [62.89251403093734]
  BinSeek is the first two-stage cross-modal retrieval framework for stripped binary code analysis.<n>It consists of two models: BinSeekEmbedding is trained on large-scale dataset to learn the semantic relevance of the binary code.<n>BinSeek-Reranker learns to carefully judge the relevance of the candidate code to the description with context augmentation.
  arXiv  Detail & Related papers  (2025-12-11T07:58:10Z)
• Can LLMs Recover Program Semantics? A Systematic Evaluation with Symbolic Execution [1.5377279217726239]
  Obfuscation poses a persistent challenge for software engineering tasks such as program comprehension, maintenance, testing, and vulnerability detection.<n>We investigate whether fine-tuned language models can effectively deobfuscate programs and restore analyzability.
  arXiv  Detail & Related papers  (2025-11-24T13:55:20Z)
• Context-Guided Decompilation: A Step Towards Re-executability [50.71992919223209]
  Binary decompilation plays an important role in software security analysis, reverse engineering and malware understanding.<n>Recent advances in large language models (LLMs) have enabled neural decompilation, but the generated code is typically only semantically plausible.<n>We propose ICL4Decomp, a hybrid decompilation framework that leverages in-context learning (ICL) to guide LLMs toward generating re-executable source code.
  arXiv  Detail & Related papers  (2025-11-03T17:21:39Z)
• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• ASMA-Tune: Unlocking LLMs' Assembly Code Comprehension via Structural-Semantic Instruction Tuning [33.53059396922164]
  Assembly code analysis and comprehension play critical roles in applications like reverse engineering.<n>Traditional masked language modeling approaches do not explicitly focus on natural language interaction.<n>We present Assembly Augmented Tuning, an end-to-end structural-semantic instruction tuning framework.
  arXiv  Detail & Related papers  (2025-03-14T17:36:08Z)
• EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking [58.15568681219339]
  We introduce EquiBench, a new benchmark for evaluating large language models (LLMs)<n>This task directly tests a model's ability to reason about program semantics.<n>We evaluate 19 state-of-the-art LLMs and find that in the most challenging categories, the best accuracies are 63.8% and 76.2%, only modestly above the 50% random baseline.
  arXiv  Detail & Related papers  (2025-02-18T02:54:25Z)
• ReF Decompile: Relabeling and Function Call Enhanced Decompile [50.86228893636785]
  The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages.<n>This task supports various reverse engineering applications, such as vulnerability identification, malware analysis, and legacy software migration.
  arXiv  Detail & Related papers  (2025-02-17T12:38:57Z)
• Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement [43.2637367483626]
  Decompilation transforms compiled code back into a high-level programming language when source code is unavailable. Previous work has primarily focused on enhancing decompilation performance by increasing the scale of model parameters or training data for pre-training. By integrating these two methods, we achieved a Re-Executability performance improvement of approximately 3.90% on the Decompile-Eval benchmark, establishing a new state-of-the-art performance of 52.41%.
  arXiv  Detail & Related papers  (2024-06-25T02:37:53Z)
• FoC: Figure out the Cryptographic Functions in Stripped Binaries with LLMs [51.898805184427545]
  We propose a novel framework called FoC to Figure out the Cryptographic functions in stripped binaries.<n>We first build a binary large language model (FoC-BinLLM) to summarize the semantics of cryptographic functions in natural language.<n>We then build a binary code similarity model (FoC-Sim) upon the FoC-BinLLM to create change-sensitive representations and use it to retrieve similar implementations of unknown cryptographic functions in a database.
  arXiv  Detail & Related papers  (2024-03-27T09:45:33Z)
• LLM4Decompile: Decompiling Binary Code with Large Language Models [10.346311290153398]
  Decompilation aims to convert binary code to high-level source code, but traditional tools like Ghidra often produce results difficult to read and execute. We propose LLM4Decompile, the first and largest open-source LLM series (1.3B to 33B) trained to decompile binary code. The resulting models significantly outperform GPT-4o and Ghidra on the HumanEval and ExeBench benchmarks by over 100% in terms of re-executability rate.
  arXiv  Detail & Related papers  (2024-03-08T13:10:59Z)
• SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization [51.67317895094664]
  This paper studies file-level code summarization, which can assist programmers in understanding and maintaining large source code projects. We propose SparseCoder, an identifier-aware sparse transformer for effectively handling long code sequences.
  arXiv  Detail & Related papers  (2024-01-26T09:23:27Z)
• LILO: Learning Interpretable Libraries by Compressing and Documenting Code [71.55208585024198]
  We introduce LILO, a neurosymbolic framework that iteratively synthesizes, compresses, and documents code. LILO combines LLM-guided program synthesis with recent algorithmic advances in automated from Stitch. We find that AutoDoc boosts performance by helping LILO's synthesizer to interpret and deploy learned abstractions.
  arXiv  Detail & Related papers  (2023-10-30T17:55:02Z)
• Boosting Neural Networks to Decompile Optimized Binaries [13.255618541522436]
  Decompilation aims to transform a low-level program language (LPL) into its functionally-equivalent high-level program language (HPL) We propose a novel learning-based approach named NeurDP, that targets compiler-optimized binaries.
  arXiv  Detail & Related papers  (2023-01-03T06:45:54Z)
• Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model [57.92200214957124]
  External language models (LMs) are used to improve the recognition performance of end-to-end (E2E) automatic speech recognition (ASR) systems. We propose a novel decoding algorithm where a word-level lattice is constructed on-the-fly to consider all possible word sequences. Our method consistently outperforms subword-level LMs, including N-gram LM and neural network LM.
  arXiv  Detail & Related papers  (2022-01-06T10:04:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.