EUVIMEDEUVIMED entdecken
Crossref

Toward Zero-Shot Multi-Label Identification of Attack Techniques: Enhancing LLM Reasoning With Semantic Evidence Discovery

Ziyu Wang, Zhanhao Fan, Yanjun Li, Xing Zhang, Peng Dai, Zhihong Tian

IEEE Transactions on Knowledge and Data Engineering · 2026-07 · 38 (7) · 4791-4804

DOI: 10.1109/tkde.2026.3682468 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-07. Verfasst von Ziyu Wang und 5 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Key Laboratory of Industrial Control System Security, Guangdong S&T Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately mapping unstructured cyber threat intelligence (CTI) text to standardized attack technique remains a fundamental yet challenging task, especially under zero-shot conditions where no labeled instances from the target CTI corpus are available. Existing methods largely rely on heuristic rules or supervised classifiers,and therefore often generalize poorly to unseen, long-tail, or evolving techniques. To overcome these limitations, we propose RA-CTI—a retrieval-augmented Large Language Model (LLM) framework for contextual technique identification, which instantiates a general Retrieve–Expand–Infer paradigm for aligning free-form text with ontology-driven label inventories. RA-CTI reformulates MITRE ATT&CK Techniques Identification as semantic evidence discovery and reference-guided reasoning through three coordinated stages: 1) dense semantic retrieval for efficient candidate acquisition, 2) query expansion and evidence aggregation to improve recall and coverage, and 3) reference-aware inference that conditions on explicit MITRE ATT&CK technique definitions for fine-grained semantic alignment. An optional weakly supervised retriever adaptation module further improves domain robustness without relying on manual annotations. Extensive experiments on multiple public CTI datasets show that RA-CTI consistently outperforms state-of-the-art baselines in zero-shot multi-label identification, achieving better efficiency–accuracy trade-offs and strong generalization across LLM backbones.

Förderung

  • National Natural Science Foundation of China
  • Guangdong Key Laboratory of Industrial Control System Security
  • Guangdong S&T Program

Zitieren

APA

Wang, Z., Fan, Z., Li, Y., Zhang, X., Dai, P., & Tian, Z. (2026). Toward Zero-Shot Multi-Label Identification of Attack Techniques: Enhancing LLM Reasoning With Semantic Evidence Discovery. IEEE Transactions on Knowledge and Data Engineering, 38(7), 4791-4804. https://doi.org/10.1109/tkde.2026.3682468

Vancouver

Wang Z, Fan Z, Li Y, Zhang X, Dai P, Tian Z. Toward Zero-Shot Multi-Label Identification of Attack Techniques: Enhancing LLM Reasoning With Semantic Evidence Discovery. IEEE Transactions on Knowledge and Data Engineering. 2026;38(7):4791-4804. doi:10.1109/tkde.2026.3682468

BibTeX
@article{Wang2026,
  author = {Wang, Ziyu and Fan, Zhanhao and Li, Yanjun and Zhang, Xing and Dai, Peng and Tian, Zhihong},
  title = {Toward Zero-Shot Multi-Label Identification of Attack Techniques: Enhancing LLM Reasoning With Semantic Evidence Discovery},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {7},
  pages = {4791--4804},
  doi = {10.1109/tkde.2026.3682468}
}
Kostenlos starten →