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

2026-02-10

AI Summary

This work addresses the limitations of existing binary function similarity search systems, which predominantly rely on dual-encoder architectures that struggle to capture fine-grained interactions between query and candidate functions, thereby constraining retrieval accuracy. To overcome this, we propose ReSIM, the first system to integrate a neural re-ranking mechanism into binary code similarity search. Building upon conventional embedding-based retrieval, ReSIM introduces a joint modeling module that enables refined re-ranking of candidate functions, effectively circumventing the independence constraint inherent in dual-encoder approaches. This advancement significantly enhances the model’s capacity for accurate similarity assessment. Comprehensive evaluation across two benchmark datasets using seven diverse embedding models demonstrates that ReSIM achieves an average improvement of 21.7% in nDCG and 27.8% in Recall.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Computer Vision: Image and Video Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web search models and ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

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.

Problem

• Binary Function Similarity
• Function Search
• Embedding-based Retrieval
• Bi-encoder Limitation
• Similarity Ranking

Innovation

• neural re-ranker
• binary function similarity
• bi-encoder limitation
• joint representation
• function search