2024 · Conference paper
ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries
Combines two fine-tuned language models with Prolog-based cross-function reasoning to infer local-variable symbols and user-defined data structures from stripped-binary decompilation.
Scope and limitations
The method depends on underlying decompilation and learned predictions over C/C++ data. Cross-checking reduces conflicting predictions but does not prove that recovered names or layouts match the unavailable source. The public artifact includes models, processed data, and evaluation code.
Why it fits this collection
A concrete hybrid approach for grounding LLM-generated reverse-engineering annotations in program analysis.
Publication and review details
- Venue
- ACM CCS 2024
- Status
- Conference paper
- Publication / posting date
- December 2, 2024
- Date source
- ACM-deposited Crossref print-publication date; the October 14–18 CCS 2024 conference week is not used as the publication date.
- DOI
- 10.1145/3658644.3670340
ACM metadata records print publication on 2024-12-02 and online publication on 2024-12-09, pages 4554–4568. The author-hosted published PDF identifies the event as CCS ’24, held October 14–18, 2024 in Salt Lake City. The DOI, title, six authors and venue agree with the publisher record and the official author artifact.
Sources reviewed
Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.