An online KS-statistic monitor detects shifts in deployed safety classifiers with 86.6% valid detection rate, exposes conformal prediction collapse in high-dimensional embeddings, and derives a confidence-gated security boundary against adaptive attackers.
WATCH : Adaptive monitoring for AI deployments via weighted-conformal martingales
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A composite multi-proxy framework detects harmful drift in label-free risk decision systems and enables graduated governance alerts.
A new evidence sufficiency model with four dimensions and seven proxy categories enables monitoring of ML risk systems under delayed ground truth, detecting covariate and mixed drift but not concept drift without feature changes.
citing papers explorer
-
Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers
An online KS-statistic monitor detects shifts in deployed safety classifiers with 86.6% valid detection rate, exposes conformal prediction collapse in high-dimensional embeddings, and derives a confidence-gated security boundary against adaptive attackers.