cs.CRNov 5, 2026

MEvince: Knowledge-Constrained LLM Reasoning for Technique Identification from Malware Reports

Authors: Hongyu She, Yiling He, Mengda Xie, Yiping Liu, Xingzhi Qian, Zhan Qin, Lorenzo Cavallaro

Organizations: Zhejiang University Hangzhou, China · University College London London, United Kingdom · Jiangsu Police Institute Nanjing, China · Alibaba Group Beijing, China

Abstract

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.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution

    May 7, 2026Christopher G. Pedraza Pohlenz, Hassan Jalil Hadi, Ali Hassan +1LLMs for CybersecurityMalware Analysis

  2. Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence

    Aug 7, 2026Jiayun Zhang, Junshen Xu, Zejun Xie +1Cyber Threat IntelligenceCybersecurity

  3. Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports

    Jun 16, 2026Ahmed Ryan, Saad Sakib Noor, Md Erfan +3LLM EvaluationCyber Threat Intelligence