StageFinder fuses graph neural networks on provenance data with LSTMs to estimate APT attack stages aligned with MITRE ATT&CK, achieving 0.96 macro F1 on DARPA datasets.
A novel approach for apt attack detection based on an intelligent behavior profile and deep graph network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning the APT Kill Chain: Temporal Reasoning over Provenance Data for Attack Stage Estimation
StageFinder fuses graph neural networks on provenance data with LSTMs to estimate APT attack stages aligned with MITRE ATT&CK, achieving 0.96 macro F1 on DARPA datasets.