DRIFT uses hybrid character and subword tokenization plus multi-task self-supervised pre-training to build DGA detectors that resist temporal drift and outperform baselines in forward-chaining evaluations over nine years of data.
An evaluation of DGA classifiers
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection
DRIFT uses hybrid character and subword tokenization plus multi-task self-supervised pre-training to build DGA detectors that resist temporal drift and outperform baselines in forward-chaining evaluations over nine years of data.