Metraipolis › archive › dc_a63fcf867eef
MEvince: Knowledge-Constrained LLM Reasoning for Technique Identification from Malware Reports — arXiv:2611.07486
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07486
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:43:20.160Z
- SHA-256 of the archived text
abc9102ced8111687187010b3d357e718e208f3f10780112a4556c3cdf190775- Stable URL of this page
https://metraipolis.com/documento/dc_a63fcf867eef
How to cite
MEvince: Knowledge-Constrained LLM Reasoning for Technique Identification from Malware Reports — arXiv:2611.07486 — arXiv (en), https://arxiv.org/abs/2611.07486 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a63fcf867eef (Metraipolis archive dc_a63fcf867eef, sha256 abc9102ced8111687187010b3d357e718e208f3f10780112a4556c3cdf190775)
BibTeX
@misc{dca63fcf867eef,
title = {MEvince: Knowledge-Constrained LLM Reasoning for Technique Identification from Malware Reports — arXiv:2611.07486},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07486},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a63fcf867eef; sha256 abc9102ced8111687187010b3d357e718e208f3f10780112a4556c3cdf190775},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07486. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Mapping behavioral intelligence in malware analysis reports to ATT&CK techniques supports threat analysis and defense, but reliable identification remains challenging. Supporting evidence is often scattered across long, heterogeneous reports, while closely related techniques share behavioral cues and differ only in subtle but decisive details. While large language models (LLMs) can use external knowledge to interpret reports, they may assign techniques based on plausible associations rather than sufficient evidence. We present MEvince, a knowledge-constrained LLM reasoning framework for report-level malware technique identification. Its core is a shared behavioral representation connecting report observations to technique definitions. This representation is built through agentic mining of technique documentation and supports two online stages: 1) primitive-guided extraction uses behavioral primitives to structure LLM-extracted observations, link them to source passages, and group dispersed evidence; 2) evidence-aligned retrieval matches this evidence to technique profiles through the same concepts, retaining likely candidates and confusable alternatives for LLM comparison of distinguishing behaviors. Controls at both stages validate evidence references and check technique-specific requirements. The representation also supports adaptation without parameter updates, where offline agentic audits diagnose concept weaknesses and refine extraction or retrieval policies. We evaluate MEvince against 11 baselines spanning four method families using a dataset of 610 public malware reports referenced by MITRE ATT&CK. MEvince improves exact-ID F1 over the strongest baseline by 17.4%, and its concept-guided retrieval increases gold-label candidate coverage from 31.6% to 47.9%. With a small adaptation set, offline refinement yields further gains and outperforms baselines that update model parameters. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Computation and Language (cs.CL); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2611.07486 — 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 2026-11-06T14:18:57.596Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).