ML Security PapersGuided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
Charmaine Barker, Daniel Bethell, Simos Gerasimou · University of York
Post-hoc evidential meta-model detects adversarial inputs and OOD samples via noise-driven uncertainty curriculum on frozen models
Reliable uncertainty quantification remains a major obstacle to the deployment of deep learning models under distributional shift. Existing post-hoc approaches that retrofit pretrained models either inherit misplaced confidence or merely reshape predictions, without teaching the model when to be uncertain. We introduce GUIDE, a lightweight evidential learning meta-model approach that attaches to a frozen deep learning model and explicitly learns how and when to be uncertain. GUIDE identifies salient internal features via a calibration stage, and then employs these features to construct a noise-driven curriculum that teaches the model how and when to express uncertainty. GUIDE requires no retraining, no architectural modifications, and no manual intermediate-layer selection to the base deep learning model, thus ensuring broad applicability and minimal user intervention. The resulting model avoids distilling overconfidence from the base model, improves out-of-distribution detection by ~77% and adversarial attack detection by ~80%, while preserving in-distribution performance. Across diverse benchmarks, GUIDE consistently outperforms state-of-the-art approaches, evidencing the need for actively guiding uncertainty to close the gap between predictive confidence and reliability.