# How Machine Learning Is Solving the Binary Function Similarity Problem > Measures binary function similarity research by re-implementing ten representative approaches from the security, programming-language and machine-learning communities in one IDA Pro-based framework, from fuzzy hashing (Catalog1, FunctionSimSearch) to graph neural network, NLP-encoder and transformer models. Two new datasets support six tasks that vary optimization, compiler, bitness and architecture, scored by AUC and ranking metrics, plus a firmware vulnerability-search case. The authors report that fuzzy hashing fails in harder cross-architecture settings, GNN-based models perform best in almost all tasks, and many recent models score similarly on common data. - Authors: Andrea Marcelli; Mariano Graziano; Xabier Ugarte-Pedrero; Yanick Fratantonio; Mohamad Mansouri; Davide Balzarotti - Venue: USENIX Security 2022 - Status: Conference paper - Publication / posting date: August 2022 - Date source: Publication month from the official USENIX BibTeX (month = aug) and the final PDF cover for the 31st USENIX Security Symposium, August 10–12, 2022; no exact publication day is asserted. - Sources reviewed: 2026-10-20 - Added to the catalog: 2026-11-03 - Original paper: - PDF: - Code: - BibTeX: - Catalog page: - Record JSON: - Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-binary-function-similarity/index.md) ## Scope and limitations A 2022 comparison of the authors’ re-implementations, not of the original papers’ code or reported numbers, which the authors did not try to reproduce; CodeCMR was run by its own authors, and Trex was tested only on Dataset-2 with its authors’ model. Dynamic-analysis, symbolic-execution and other slow direct-comparison approaches were excluded by design, and LLM-based similarity models are not covered. Dataset-1 compiles seven open-source projects (ClamAV, Curl, Nmap, OpenSSL, Unrar, Z3, Zlib) with GCC and Clang for x86-64, ARM and MIPS in 32 and 64 bit at O0–O3 and Os with function inlining disabled, and drops functions under five basic blocks. Dataset-2 reuses ten GCC 7.5 projects released by the Trex authors. Feature extraction depends on IDA Pro 7.3; BinaryAI covered only part of the data because a recent Hex-Rays MIPS decompiler license was unavailable. The firmware case searches ten OpenSSL functions in two images. Obfuscated code is not evaluated, and the results are not a current ranking. ## Why it fits this collection Adds a common-framework measurement of binary function matching, which reverse engineers use to transfer labels from known functions to stripped code, complementing single-model records such as jTrans and BinaryAI. ## Publication and review notes No paper DOI or arXiv identifier was verified; the record uses the reviewed USENIX Security presentation-page and sec22-marcelli.pdf profile. The USENIX BibTeX gives the 31st USENIX Security Symposium, pages 2099–2116, USENIX Association and month August; the presentation page also links a prepublication PDF and slides. The repository README lists errata for a Section 3.2 statement on BinDiff and Diaphora cross-architecture support and for the Figure 2 captions. At reviewed commit f0da093 (2024-05-15), repository code is MIT-licensed, but the README lists GPL-3.0 (Catalog1, SAFE, IDA CodeCMR plugin), LGPL-2.1 (Gensim-based Asm2vec), Apache-2.0 (FunctionSimSearch, GGSNN/GMN) and CC BY-NC-SA 4.0 (GNN-s2v) components; compiled binaries keep their own licenses. Binaries (about 15 GB) and extracted features (about 38 GB) download from Google Drive, and generating new IDBs or features requires IDA Pro. ## Primary sources 1. 2. 3. 4. 5. 6. 7. ## About this entry Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX. Original editorial content: MIT. Linked projects, papers and assets retain their own rights and licenses.