# XDA: Accurate, Robust Disassembly with Transfer Learning

arXiv: https://arxiv.org/abs/2010.00770 · HTML: https://mlsanity.com/paper/2010.00770/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2020.

## Built on by (most cited first, 21 of 21)

- [Frontier AI's Impact on the Cybersecurity Landscape](https://mlsanity.com/paper/2504.05408/) (2025)
- [CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision](https://mlsanity.com/paper/2402.16928/) (2024)
- [Beyond the C: Retargetable Decompilation using Neural Machine Translation](https://mlsanity.com/paper/2212.08950/) (2022)
- [Pop Quiz! Can a Large Language Model Help With Reverse Engineering?](https://mlsanity.com/paper/2202.01142/) (2022)
- [Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models](https://mlsanity.com/paper/2312.09601/) (2023)
- [Assemblage: Automatic Binary Dataset Construction for Machine Learning](https://mlsanity.com/paper/2405.03991/) (2024)
- [Boosting Neural Networks to Decompile Optimized Binaries](https://mlsanity.com/paper/2301.00969/) (2023)
- [kTrans: Knowledge-Aware Transformer for Binary Code Embedding](https://mlsanity.com/paper/2308.12659/) (2023)
- [Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases](https://mlsanity.com/paper/2405.19581/) (2024)
- [TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models](https://mlsanity.com/paper/2405.16783/) (2024)
- [Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive Learning](https://mlsanity.com/paper/2111.01415/) (2021)
- [NeuDep: Neural Binary Memory Dependence Analysis](https://mlsanity.com/paper/2210.02853/) (2022)
- [VulCatch: Enhancing Binary Vulnerability Detection through CodeT5 Decompilation and KAN Advanced Feature Extraction](https://mlsanity.com/paper/2408.07181/) (2024)
- [Tady: A Neural Disassembler without Structural Constraint Violations](https://mlsanity.com/paper/2506.13323/) (2025)
- [Cybersecurity is the True Frontier for Generative AI Success or Failure](https://mlsanity.com/paper/2606.28929/) (2026)
- [Transfer Learning for Security: Challenges and Future Directions](https://mlsanity.com/paper/2403.00935/) (2024)
- [A Progressive Transformer for Unifying Binary Code Embedding and Knowledge Transfer](https://mlsanity.com/paper/2412.11177/) (2024)
- [A Deep Dive into Function Inlining and its Security Implications for ML-based Binary Analysis](https://mlsanity.com/paper/2512.14045/) (2025)
- [On the Role of Pre-trained Embeddings in Binary Code Analysis](https://mlsanity.com/paper/2502.08682/) (2025)
- [SoK: AI-Augmented Binary Reversing](https://mlsanity.com/paper/2606.17398/) (2026)
- [Reveree: Diagnosing LLM Reverse-Engineering Agents](https://mlsanity.com/paper/2609.01185/) (2026)

## Abstract (arXiv)

Accurate and robust disassembly of stripped binaries is challenging. The root of the difficulty is that high-level structures, such as instruction and function boundaries, are absent in stripped binaries and must be recovered based on incomplete information. Current disassembly approaches rely on heuristics or simple pattern matching to approximate the recovery, but these methods are often inaccurate and brittle, especially across different compiler optimizations. We present XDA, a transfer-learning-based disassembly framework that learns different contextual dependencies present in machine code and transfers this knowledge for accurate and robust disassembly. We design a self-supervised learning task motivated by masked Language Modeling to learn interactions among byte sequences in binaries. The outputs from this task are byte embeddings that encode sophisticated contextual dependencies between input binaries' byte tokens, which can then be finetuned for downstream disassembly tasks. We evaluate XDA's performance on two disassembly tasks, recovering function boundaries and assembly instructions, on a collection of 3,121 binaries taken from SPEC CPU2017, SPEC CPU2006, and the BAP corpus. The binaries are compiled by GCC, ICC, and MSVC on x86/x64 Windows and Linux platforms over 4 optimization levels. XDA achieves 99.0% and 99.7% F1 score at recovering function boundaries and instructions, respectively, surpassing the previous state-of-the-art on both tasks. It also maintains speed on par with the fastest ML-based approach and is up to 38x faster than hand-written disassemblers like IDA Pro. We release the code of XDA at https://github.com/CUMLSec/XDA.