2019 · Conference paper
DIRE: A Neural Approach to Decompiled Identifier Naming
Combines lexical and structural information from decompiler output to predict meaningful variable names, with a training and evaluation corpus derived from compiled C projects.
Scope and limitations
This is learned identifier naming, not complete source reconstruction or an autonomous agent. Its reported results concern an x86-64 C corpus and depend on decompiler output. The original author repository is deprecated and points to a successor.
Why it fits this collection
A foundational reference for the renaming step frequently delegated to reverse-engineering assistants.
Publication and review details
- Venue
- ASE 2019
- Status
- Conference paper
- Publication / posting date
- November 2019
- Date source
- Publisher-deposited Crossref print-publication month; the 11–15 November 2019 conference dates are not used to assert a publication day.
- First arXiv submission
- September 19, 2019
- arXiv
- 1909.09029
- Reviewed arXiv version
- v2
- DOI
- 10.1109/ASE.2019.00064
IEEE/ACM ASE 2019 proceedings, pages 628–639; the DOI resolves to IEEE Xplore document 8952404. The publisher-deposited and arXiv titles use 'Naming'; the ASE program and original code repository use the variant 'Renaming'. Both refer to this paper. Crossref lists 'Edward Schwartz'; the paper's own 'Edward J. Schwartz' is retained. Code URL is the verified original author artifact, explicitly deprecated, rather than a claim of current package support.
Sources reviewed
Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.
Primary sources
- https://doi.org/10.1109/ASE.2019.00064
- https://api.crossref.org/works/10.1109/ASE.2019.00064
- https://arxiv.org/abs/1909.09029
- https://2019.ase-conferences.org/details/ase-2019-papers/49/DIRE-A-Neural-Approach-to-Decompiled-Identifier-Renaming
- https://github.com/pcyin/dire
- https://github.com/CMUSTRUDEL/DIRTY