2018 · Preprint
A Cross-Architecture Instruction Embedding Model for Natural Language Processing-Inspired Binary Code Analysis
The paper learns instruction embeddings that capture semantic relationships within and across architectures. It evaluates them on semantic basic-block comparison, outperforming a code-statistics approach.
Scope and limitations
Evaluates semantic basic-block comparison across architectures on disassembled binary code.
Why it fits this collection
It addresses cross-architecture binary code analysis through learned instruction representations.
Publication and review details
- Venue
- arXiv
- Status
- Preprint
- Publication / posting date
- December 23, 2018
- Date source
- First arXiv submission date.
- First arXiv submission
- December 23, 2018
- arXiv
- 1812.09652
- Reviewed arXiv version
- v1
The date and venue come from the arXiv record.
Sources reviewed
Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.