Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning

• URL: http://arxiv.org/abs/2607.09452v1
• Date: Fri, 10 Jul 2026 14:22:30 GMT
• Title: Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning
• Abstract summary: We present a practical pipeline for recovering source code from stripped binary functions.<n>Our binary-to-source-code retrieval method attempts to identify the source function from a source code database.
• Score: 3.9488518969307305
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code retrieval, and large language model reasoning. Our binary-to-source-code retrieval method attempts to identify the source function from a source code database, rather than generating approximate decompiled pseudocode. It extracts anchors such as strings, constants, external calls, and available function names using Ghidra, retrieves candidate files via an inverted-index search database, narrows candidates to likely function snippets, and re-ranks them with a large language model (LLM) based on disassembly, decompiled code, and source metadata. Confident matches can also serve as anchors in later passes. In an evaluation backed by our high-fidelity source code database on a stripped, optimized tcpdump binary, our proposed binary-to-source matching method achieves 95.2% assembly instruction coverage. Experiments on a GitHub-based retrieval database showed lower performance with 35.5% instruction coverage on average, mainly due to retrieval misses. These results show that source-level binary recovery excels with high-quality databases and remains a useful tool in noisy environments.

Related papers

• SBridge: Identifying Source-to-Binary Function Similarity via Cross-Domain Control Block Matching [3.905466484594527]
  SBridge is a precise approach for identifying functions in binaries that are similar to the given source code functions.<n>For evaluation, we collected 3,904 real-world C/C++ binaries from BinKit.
  arXiv  Detail & Related papers  (2026-06-26T13:03:43Z)
• Decaf: Improving Neural Decompilation with Automatic Feedback and Search [64.02615739798277]
  High-level syntax, identifiers, and custom data types are generally lost as the compiler translates human-readable code to low-level machine code.<n>Generative AI models are a natural fit for reconstructing high-level syntax, identifiers, and types.<n>We argue that compiler feedback can be used to dramatically improve the semantic correctness of neural decompiler outputs via search.
  arXiv  Detail & Related papers  (2026-05-12T04:21:26Z)
• AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion [55.21541958868449]
  We propose AlignCoder, a repository-level code completion framework.<n>Our framework generates an enhanced query that bridges the semantic gap between the initial query and the target code.<n>We employ reinforcement learning to train an AlignRetriever that learns to leverage inference information in the enhanced query for more accurate retrieval.
  arXiv  Detail & Related papers  (2026-01-27T15:23:14Z)
• 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)
• SALT4Decompile: Inferring Source-level Abstract Logic Tree for LLM-Based Binary Decompilation [17.58664677898224]
  saltm is a novel binary decompilation method that abstracts stable logical features between binary and source code.<n>saltm is highly effective in recovering the logic of the source code, significantly outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-18T05:57:15Z)
• Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation [18.28488002922524]
  Decompile-Bench is the first open-source dataset comprising two million binary-source function pairs condensed from 100 million collected function pairs.<n>For the evaluation purposes, we developed a benchmark Decompile-Bench-Eval including manually crafted binaries from the well-established HumanEval and MBPP.<n>We find that fine-tuning with Decompile-Bench causes a 20% improvement over previous benchmarks in terms of the re-executability rate.
  arXiv  Detail & Related papers  (2025-05-19T03:34:33Z)
• An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding [50.17907898478795]
  This work proposes a benchmark to evaluate the effectiveness of Large Language Models (LLMs) in real-world reverse engineering scenarios.<n>Our evaluations reveal that existing LLMs can understand binary code to a certain extent, thereby improving the efficiency of binary code analysis.
  arXiv  Detail & Related papers  (2025-04-30T17:02:06Z)
• 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)
• RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation [96.75695811963242]
  RepoCoder is a framework to streamline the repository-level code completion process. It incorporates a similarity-based retriever and a pre-trained code language model. It consistently outperforms the vanilla retrieval-augmented code completion approach.
  arXiv  Detail & Related papers  (2023-03-22T13:54:46Z)
• Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries [4.0484792045035505]
  We extend large pre-trained language models of source code to summarise decompiled binary functions. We investigate the impact of input and data properties on the performance of such models. BinT5 achieves the state-of-the-art BLEU-4 score of 60.83, 58.82, and 44.21 for summarising source, decompiled, and synthetically stripped decompiled code.
  arXiv  Detail & Related papers  (2023-01-04T16:56:33Z)
• Improving type information inferred by decompilers with supervised machine learning [0.0]
  In software reverse engineering, decompilation is the process of recovering source code from binary files. We build different classification models capable of inferring the high-level type returned by functions. Our system is able to predict function return types with a 79.1% F1-measure, whereas the best decompiler obtains a 30% F1-measure.
  arXiv  Detail & Related papers  (2021-01-19T11:45:46Z)

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.