3 papers
cs.LG2026
Erased, but Not Gone: Output Forgetting Is Not True Forgetting
Teresa Pui Yee Yong, Win Kent Ong, Chee Seng Chan
Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced logit-level membership inference. But if output-level success can coexis…
cs.LG2025
Ten Challenging Problems in Federated Foundation Models
Tao Fan, Hanlin Gu, Xuemei Cao +30
Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of fed…
cs.LG2025
Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
Hanlin Gu, Win Kent Ong, Chee Seng Chan +1
The advent of Federated Learning (FL) highlights the practical necessity for the right to be forgotten for all clients, allowing them to request data deletion from the machine lear…