[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81604-en":3,"doc-seo-81604-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},81604,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Practical Type Inference High Throughput Recovery of Real World Structures and Function Signatures","Binary type recovery from stripped executables underpins exact decompilation, but practical deployments remain constrained by layout and semantic fidelity requirements, especially for composite structures. Existing solutions often synthesize layouts or infer names after the fact and frequently introduce excessive runtime overhead, reducing pipeline usability. XTRIDE introduces a highly optimized n-gram-based method with actionable confidence scores for automated use, achieving 70–2300× speedups and the highest ratio of fully correct struct layouts. Optimized training yields 90.15% accuracy overall and a 5.09-point improvement on DIRT. It also generalizes to function signature recovery on embedded firmware.","Practical Type Inference: High-Throughput Recovery of Real-World Structures and Function Signatures  \nLukas Seidel RevEng.AI & TU Berlin  \nGermany, Berlin [lukas.seidel@reveng.ai](lukas.seidel@reveng.ai)  \nSam L. Thomas  \nRevEng.AI  \nUnited Kingdom, Birmingham  \nKonrad Rieck  \nTU Berlin & BIFOLD Germany, Berlin  \narXiv :2603 .08225v 3 [ cs .CR] 10 Jul 2026  \nAbstract  \nThe recovery of types from stripped binaries is a key to exact decompilation, yet its practical realization suffers. For composite structures in particular, both layout and semantic fidelity are required to enable end-to-end reconstruction. Many existing approaches either synthesize layouts or infer names post-hoc, which weakens downstream usability. This is further aggravated by an excessive runtime overhead that is especially prohibitive in automated environments. We present XTRIDE, an improved n-gram-based approach that focuses on practicality: highly optimized throughput and actionable confidence scores allow for deployment in automated pipelines. When compared to the state of the art in struct recovery, our method achieves comparable performance while being between 70 and 2300× faster. As our inference is grounded in real-world types, we achieve the highest ratio of fully-correct struct layouts. With an optimized training regimen, our model outperforms the current state of the art on the DIRT dataset by 5.09 percentage points, achieving 90.15% type inference accuracy overall. Furthermore, we show that n-gram-based type prediction generalizes to function signature recovery: conducting a case study on embedded firmware, we show that this efficient approach to function similarity can assist in typical reverse engineering tasks.  \nACM Reference Format:  \nLukas Seidel, Sam L. Thomas, and Konrad Rieck. 2026. Practical Type Inference: High-Throughput Recovery of Real-World Structures and Function Signatures. In Proceedings of (PREPRINT of Work accepted at ACM CODASPY ’26). ACM, New York, NY, USA, 12 pages. [https://doi.org/XXXXXXX](https://doi.org/XXXXXXX). XXXXXXX  \n1 Introduction  \nBinary reverse engineering is critical for security applications such as malware analysis, vulnerability detection, general code understanding and automated program analysis. A core challenge in this field is the recovery of structural information from binaries, especially stripped ones where variable types, names, and data structures are irrevocably lost during compilation. Recovering this missing type information is essential for producing readable, analyzable decompiler output that can support downstream tasks.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nPREPRINT of Work accepted atACM CODASPY’26,  \n© 2026 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-x-xxxx-xxxx-x/YYYY/MM  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nWhile recent advances in machine learning and static analysis have improved type recovery capabilities, practical deployment remains challenging. Particularly for user-defined structures, both layout fidelity and semantic information are required. Many existing approaches either synthesize layouts without recovering meaningful names [36], or leverage large language models that incur prohibitive runtime overhead [6, 35] . Furthermore, most type recovery systems do not provide a principled mechanism for est","cbCaikSfFvaWopwh","https://ap.wps.com/l/cbCaikSfFvaWopwh","pdf",590427,1,12,"English","en",105,"# Introduction\n## Binary reverse engineering and structural recovery\n## Challenges in practical type recovery\n## Related work and limitations\n# XTRIDE approach\n## Improved n-gram-based type recovery","[{\"question\":\"What problem does the paper address in binary reverse engineering?\",\"answer\":\"It addresses recovering type information from stripped binaries so decompilers can reconstruct meaningful structural details, especially for user-defined composite structures.\"},{\"question\":\"What makes the proposed XTRIDE approach practical for automated pipelines?\",\"answer\":\"XTRIDE is an optimized n-gram-based method designed for high throughput and provides actionable confidence scores to support filtering and integration into automated workflows.\"},{\"question\":\"How does XTRIDE perform compared with state-of-the-art struct recovery methods?\",\"answer\":\"It achieves comparable performance to the state of the art in struct recovery while being 70 to 2300 times faster, with the highest ratio of fully correct struct layouts and 90.15% overall type inference accuracy.\"}]",1784174681,30,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"practical-type-inference-high-throughput-recovery-of-real-world-structures-and-function-signatures","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/practical-type-inference-high-throughput-recovery-of-real-world-structures-and-function-signatures/81604/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in binary reverse engineering?","Question",{"text":75,"@type":76},"It addresses recovering type information from stripped binaries so decompilers can reconstruct meaningful structural details, especially for user-defined composite structures.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What makes the proposed XTRIDE approach practical for automated pipelines?",{"text":80,"@type":76},"XTRIDE is an optimized n-gram-based method designed for high throughput and provides actionable confidence scores to support filtering and integration into automated workflows.",{"name":82,"@type":73,"acceptedAnswer":83},"How does XTRIDE perform compared with state-of-the-art struct recovery methods?",{"text":84,"@type":76},"It achieves comparable performance to the state of the art in struct recovery while being 70 to 2300 times faster, with the highest ratio of fully correct struct layouts and 90.15% overall type inference accuracy.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]