Metraipolis › archive › dc_80640bd25f94
MARS: Malware Analysis with Rule-Based Scoring of LLM Claims — arXiv:2610.09553
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09553
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:11:12.022Z
- SHA-256 of the archived text
ed7f6018984177d8d687b4e08458247975656328ccb3959f79fa441d6f43288a- Stable URL of this page
https://metraipolis.com/documento/dc_80640bd25f94
How to cite
MARS: Malware Analysis with Rule-Based Scoring of LLM Claims — arXiv:2610.09553 — arXiv (en), https://arxiv.org/abs/2610.09553 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_80640bd25f94 (Metraipolis archive dc_80640bd25f94, sha256 ed7f6018984177d8d687b4e08458247975656328ccb3959f79fa441d6f43288a)
BibTeX
@misc{dc80640bd25f94,
title = {MARS: Malware Analysis with Rule-Based Scoring of LLM Claims — arXiv:2610.09553},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09553},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_80640bd25f94; sha256 ed7f6018984177d8d687b4e08458247975656328ccb3959f79fa441d6f43288a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09553. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models can triage malware through direct verdicts or behavioral claims scored by an external policy. We present MARS, a malware triage framework, and compare direct classification with single-pass claim scoring using the same evidence collector and identical static evidence bundles for each model. The evaluation covers 1,195 PE and ELF binaries grouped into 1,001 near-duplicate clusters and six language models, with deterministic rules providing a baseline. Direct classification is more accurate for all six models. On samples with usable outputs from both paths, its accuracy advantage ranges from 3.7 to 20.9 percentage points, with all 95% cluster-bootstrap confidence intervals for the differences above zero. It also achieves higher malicious alert recall in ten of twelve platform and model combinations. Claim mediation provides no consistent reduction in performance variation across models. Separate subset studies find more consistent alert decisions for direct classification and a larger recall loss for the claim path when predefined indicator fields are removed. In a family identification probe, claims yield higher accuracy than verdict labels but lower accuracy than evidence text. Retained claims expose the inputs to verdict computation and permit policy revision without another model call. We reproduce archived verdicts exactly and apply a revised policy to the same records, including outputs from two additional models withdrawn by their provider. Under the evaluated claim taxonomy and additive policy, these results favor direct classification when only a verdict is required, while demonstrating that retained claims support explicit policy inspection and revision. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.09553 — 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 2026-10-08T10:14:06.102Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).