# Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity

> Trex learns execution semantics from function micro-traces, then uses that knowledge to match semantically similar binary functions.

- Authors: Kexin Pei; Zhou Xuan; Junfeng Yang; Suman Jana; Baishakhi Ray
- Venue: arXiv
- Status: Preprint
- Publication / posting date: December 16, 2020
- Date source: First arXiv submission date.
- First arXiv submission: December 16, 2020
- arXiv: 2012.08680
- Reviewed arXiv version: v3
- Sources reviewed: 2026-11-06
- Added to the catalog: 2026-11-06
- Original paper: <https://arxiv.org/abs/2012.08680>
- PDF: <https://arxiv.org/pdf/2012.08680>
- BibTeX: <https://awesomerea.org/papers/citations/paper-trex.bib>
- Catalog page: <https://awesomerea.org/papers/paper-trex/>
- Record JSON: <https://awesomerea.org/papers/paper-trex/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-trex/index.md)

## Scope and limitations

The evaluation covers 1,472,066 function binaries from 13 software projects, across architectures, compiler optimizations, and obfuscations.

## Why it fits this collection

It addresses binary function similarity by learning execution behavior from traces.

## Publication and review notes

The date and venue come from the arXiv record.

## Primary sources

1. <https://arxiv.org/abs/2012.08680>

## 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.