Variational Feature Compression for Model-Specific Representations

ArXi:2604.06644v1 Announce Type: cross As deep learning inference is increasingly deployed in shared and cloud-based settings, a growing concern is input repurposing, in which data submitted for one task is reused by unauthorized models for another. Existing privacy defenses largely focus on restricting data access, but provide limited control over what downstream uses a released representation can still. We propose a feature extraction framework that suppresses cross-model transfer while preserving accuracy for a designated classifier.