SMS: Self-Supervised Model Seeding for Verification of Machine Unlearning

Summary

The paper proposes Self-supervised Model Seeding (SMS), a scheme for verifying that a model has unlearned genuine user samples rather than only backdoored ones. SMS links user-specific seeds, original samples and the model through a self-supervised seeding task trained jointly with the primary service task. The authors report effectiveness across three datasets, several model architectures, and exact and approximate unlearning benchmarks.

Topics

• Training data and privacy