Metraipolis › archive › dc_fdc5d558512e
CHISEL-ing Back Source Code with AI-enabled Iterative Recovery — arXiv:2608.27981
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27981
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:02:57.606Z
- SHA-256 of the archived text
481bbc3647f231b5dc8c1aea373f2bfe2e63bce828fca80a3cbc32fc975cc48c- Stable URL of this page
https://metraipolis.com/documento/dc_fdc5d558512e
How to cite
CHISEL-ing Back Source Code with AI-enabled Iterative Recovery — arXiv:2608.27981 — arXiv (en), https://arxiv.org/abs/2608.27981 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fdc5d558512e (Metraipolis archive dc_fdc5d558512e, sha256 481bbc3647f231b5dc8c1aea373f2bfe2e63bce828fca80a3cbc32fc975cc48c)
BibTeX
@misc{dcfdc5d558512e,
title = {CHISEL-ing Back Source Code with AI-enabled Iterative Recovery — arXiv:2608.27981},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27981},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fdc5d558512e; sha256 481bbc3647f231b5dc8c1aea373f2bfe2e63bce828fca80a3cbc32fc975cc48c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27981. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Decompilation aims to recover high-level, compilable, and semantically equivalent code from binaries. Traditional decompilers produce pseudo-C that is difficult to read and does not compile, while the recent LLM-assisted approaches generate readable, but semantically incorrect code. LLM-aided iterative recovery is an emerging branch of research, but prior works rely on supplied test suites for semantic recovery. In this work, we present CHISEL, a test suite-free framework to iteratively recover source code from Ghidra-derived pseudo-C. CHISEL uses simple yet effective feedback from a compiler (static analysis) and a coverage-guided fuzzer (differential analysis), augmented by rich observables for grounded divergence detection and feedback, cross-iteration divergence memory, and best candidate retention. We systematically evaluate CHISEL for compilation and semantic recovery, feedback oracle soundness, and iteration overhead on 120 ExeBench functions compiled for the x86-64 architecture, across four optimizations (O0-O3), in both stripped and unstripped variants, using the open-weight Gemma4:31b LLM. CHISEL, with all recommended features, achieves an average of 96.1% re-compilability and 79.8% re-executability rates at an average of 2.1 iterations. Significantly, CHISEL recovers 26% of first-generation execution errors. At the same time, CHISEL feedback oracle falsely accepts only 9.4% candidates. Lastly, CHISEL performs significantly better than two recent prior work on LLM-assisted decompilation. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.27981 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T10:49:51.645Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).