Introduces the first public multi-source cybersecurity log dataset with per-entry ATT&CK technique labels across 12 tactics and 53 techniques and demonstrates learnability via LoRA fine-tuning of three SLMs on chunk classification and technique identification.
Automated retrieval of ATT&CK tactics and techniques for cyber threat reports,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2representative citing papers
A benchmark using a new ground-truth dataset of 2,076 complex CTI sentences shows open-source LLMs achieve at most 0.22 micro F1 on multi-label ATT&CK technique classification.
citing papers explorer
-
Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation
Introduces the first public multi-source cybersecurity log dataset with per-entry ATT&CK technique labels across 12 tactics and 53 techniques and demonstrates learnability via LoRA fine-tuning of three SLMs on chunk classification and technique identification.
-
Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports
A benchmark using a new ground-truth dataset of 2,076 complex CTI sentences shows open-source LLMs achieve at most 0.22 micro F1 on multi-label ATT&CK technique classification.