Metraipolis › archive › dc_1519bc2c2cb7

Combining LLM and Dynamic Analysis for Universal Testing of Static Application Security Testing Tools — arXiv:2610.21309

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21309
License (as archived)
CC0-1.0
Archived
2026-10-16T10:19:20.370Z
SHA-256 of the archived text
f028ae7f8ab00007aff8989473cd4b4fc9e903f5bf70c82eff9d6eba7c71b8a1
Stable URL of this page
https://metraipolis.com/documento/dc_1519bc2c2cb7

How to cite

Combining LLM and Dynamic Analysis for Universal Testing of Static Application Security Testing Tools — arXiv:2610.21309 — arXiv (en), https://arxiv.org/abs/2610.21309 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1519bc2c2cb7 (Metraipolis archive dc_1519bc2c2cb7, sha256 f028ae7f8ab00007aff8989473cd4b4fc9e903f5bf70c82eff9d6eba7c71b8a1)
BibTeX
@misc{dc1519bc2c2cb7,
  title = {Combining LLM and Dynamic Analysis for Universal Testing of Static Application Security Testing Tools — arXiv:2610.21309},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21309},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1519bc2c2cb7; sha256 f028ae7f8ab00007aff8989473cd4b4fc9e903f5bf70c82eff9d6eba7c71b8a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21309. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Static application security testing (SAST) tools help detect potential software vulnerabilities, but they themselves contain faults undermining reliability and usability. Automated testing can address these issues, yet current techniques suffer from limited program transformation diversity and lack mechanisms to verify generated variants, leading to reduced fault detection and high manual effort. We present LLM4SAST, the first universal framework detecting faults in SAST tools using large language models and dynamic feedback. Our key insight is leveraging LLMs to understand and transform code in diverse programming languages. We design novel metamorphic relations with transformations to guide variant generation, using an LLM to produce multi-language variants that satisfy these relations. To reduce erroneous variants and identify unique faults, we propose two heuristics: dynamic-feedback-driven selection and program-differencing-based clustering. For each metamorphic relation, a report-centric test oracle detects variants that fail tests and identifies underlying faults by differentially analyzing SAST reports of the seed program and its variants. LLM4SAST identified 66 unique faults across six SAST tools, with 32 confirmed or fixed after being reported to developers, demonstrating effectiveness. The proposed heuristics eliminate 47.8% of false positives, and LLM4SAST detects 3.4 times more faults while requiring only 39.8% of the variants compared to existing approaches.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.21309 — 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 2026-10-16T08:47:32.606Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).