2 papers
cs.LG2026
DISCERN: Distributional Synthetic Replay for Retain-Free Incremental Machine Unlearning
Nicolás Segura-Kunsagi, Juan Luis Suárez-Díaz, Iván Sevillano-García +1
Machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. In real deployments, however, deletion requests arri…
cs.LG2025
DCV-ROOD Evaluation Framework: Dual Cross-Validation for Robust Out-of-Distribution Detection
Arantxa Urrea-Castaño, Nicolás Segura-Kunsagi, Juan Luis Suárez-Díaz +2
Out-of-distribution (OOD) detection plays a key role in enhancing the robustness of artificial intelligence systems by identifying inputs that differ significantly from the trainin…