Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.05251 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913096659894272 |
|---|---|
| author | Wolos, Eric Doyle, Michael |
| author_facet | Wolos, Eric Doyle, Michael |
| contents | Function association is a useful process for binary reverse engineers. Search tools exist to perform association at scale, but they do not utilize the full range of capabilities that AI-enabled search provides. Prior work has explored the development of embedding models for association between certain reverse engineering code representations, but that work does not cover bidirectional association between source code and decompiled, stripped code with standard preprocessing requirements. To bridge this gap, we formalize this function association problem and evaluate the extent to which embedding models can bidirectionally associate between these two representations. To improve model performance at this task, we fine-tune a Qwen3-Embedding model with contrastive learning. We find that our new model outperforms other models on all function association baselines by a substantial margin and generalizes to a constant-algorithm association task it is not explicitly trained on. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05251 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Identifier-Free Code Embedding Models for Scalable Search Wolos, Eric Doyle, Michael Cryptography and Security Machine Learning Software Engineering Function association is a useful process for binary reverse engineers. Search tools exist to perform association at scale, but they do not utilize the full range of capabilities that AI-enabled search provides. Prior work has explored the development of embedding models for association between certain reverse engineering code representations, but that work does not cover bidirectional association between source code and decompiled, stripped code with standard preprocessing requirements. To bridge this gap, we formalize this function association problem and evaluate the extent to which embedding models can bidirectionally associate between these two representations. To improve model performance at this task, we fine-tune a Qwen3-Embedding model with contrastive learning. We find that our new model outperforms other models on all function association baselines by a substantial margin and generalizes to a constant-algorithm association task it is not explicitly trained on. |
| title | Identifier-Free Code Embedding Models for Scalable Search |
| topic | Cryptography and Security Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2605.05251 |