Aggregating multiple CTI reports improves ATT&CK technique extraction F1 by about 26 percent over single-report baselines, with saturation after 5-15 reports and maximum F1 scores of 78.6 percent and 54.9 percent across the tested campaigns.
From threat reports to continuous threat intelligence: a comparison of attack technique extraction methods from textual artifacts
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
LLM-generated adversarial fake text can perform evasion, flooding, and poisoning attacks that mislead and degrade text-based CTI pipelines.
citing papers explorer
-
Beyond Single Reports: Evaluating Automated ATT&CK Technique Extraction in Multi-Report Campaign Settings
Aggregating multiple CTI reports improves ATT&CK technique extraction F1 by about 26 percent over single-report baselines, with saturation after 5-15 reports and maximum F1 scores of 78.6 percent and 54.9 percent across the tested campaigns.
-
False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systems
LLM-generated adversarial fake text can perform evasion, flooding, and poisoning attacks that mislead and degrade text-based CTI pipelines.