Really Unlearned? Verifying Machine Unlearning via Influential Sample Pairs

Summary

IndirectVerify is a formal scheme for verifying whether machine unlearning requests have actually been executed, addressing a gap where existing verification relies on backdoor or membership inference attacks that a model provider can bypass through rapid fine-tuning. The authors generate influential sample pairs, trigger samples and reaction samples, using a perturbation-based method that alters only a small fraction of training samples so that reaction samples are misclassified. The paper claims this indirect influence provides greater robustness against bypassing than schemes that reuse the same samples throughout.

Topics

• Training data and privacy