ROAST selectively trains anomaly detectors on less vulnerable patient data with targeted outlier exposure, boosting recall by 16.2% in black-box settings and reducing training time by 88.3%.
Early prediction of sepsis from clinical data: the physionet/computing in cardiology challenge 2019.Critical care medicine, 48(2):210–217
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
-
ROAST: Risk-aware Outlier-exposure for Adversarial Selective Training of Anomaly Detectors Against Evasion Attacks
ROAST selectively trains anomaly detectors on less vulnerable patient data with targeted outlier exposure, boosting recall by 16.2% in black-box settings and reducing training time by 88.3%.