# ReSIM: Re-ranking Binary Similarity Embeddings to Improve Function Search Performance

Source: [ReSIM: Re-ranking Binary Similarity Embeddings to Improve Function Search Performance](<https://www.sota2.com/research/paper/698c0d50c97a0b3e3b5e133a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-25T05:00:07.533Z

Authors: Gianluca Capozzi, Anna Paola Giancaspro, Fabio Petroni, Leonardo Querzoni, Giuseppe Antonio Di Luna

Published: 2026-02-10T08:57:49.000Z

## Abstract

Binary Function Similarity (BFS), the problem of determining whether two binary functions originate from the same source code, has been extensively studied in recent research across security, software engineering, and machine learning communities. This interest arises from its central role in developing vulnerability detection systems, copyright infringement analysis, and malware phylogeny tools. Nearly all binary function similarity systems embed assembly functions into real-valued vectors, where similar functions map to points that lie close to each other in the metric space. These embeddings enable function search: a query function is embedded and compared against a database of candidate embeddings to retrieve the most similar matches.   Despite their effectiveness, such systems rely on bi-encoder architectures that embed functions independently, limiting their ability to capture cross-function relationships and similarities. To address this limitation, we introduce ReSIM, a novel and enhanced function search system that complements embedding-based search with a neural re-ranker. Unlike traditional embedding models, our reranking module jointly processes query-candidate pairs to compute ranking scores based on their mutual representation, allowing for more accurate similarity assessment. By re-ranking the top results from embedding-based retrieval, ReSIM leverages fine-grained relation information that bi-encoders cannot capture.   We evaluate ReSIM across seven embedding models on two benchmark datasets, demonstrating consistent improvements in search effectiveness, with average gains of 21.7% in terms of nDCG and 27.8% in terms of Recall.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Function Search on BinCorp](<https://www.sota2.com/research/sota/function-search-on-bincorp.md>): Function Search; BinCorp; nDCG@5: 91.

- [Function Search on MultiComp](<https://www.sota2.com/research/sota/function-search-on-multicomp.md>): Function Search; MultiComp; nDCG@5: 0.94.

- [Binary Function Similarity on BinCorp and MultiComp pool jointly extracted (8,441 functions)](<https://www.sota2.com/research/sota/binary-function-similarity-on-bincorp-and-multicomp-pool-jointly-extracted-8-441-functions.md>): Binary Function Similarity; BinCorp and MultiComp pool jointly extracted (8,441 functions); nDCG@5: 94.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.09548>)

[PDF](<https://arxiv.org/pdf/2602.09548.pdf>)
