ANANKE reports 97.1% TPR and 0.2% FPR for LLM-based attack investigation, but its central evaluation is compromised by knowledge-base overlap with test scenarios.
https://github.com/ shramos/Awesome-Cybersecurity-Datasets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
An Automated Attack Investigation Approach Leveraging Threat-Knowledge-Augmented Large Language Models
ANANKE reports 97.1% TPR and 0.2% FPR for LLM-based attack investigation, but its central evaluation is compromised by knowledge-base overlap with test scenarios.