The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
adversarial perturbationsdeep neural networksfine-tuning strategyforget sampleshigh-dimensional settingsmachine unlearningmodel outputsprivacy riskre-trained modelrecognition abilityresidual knowledgerurkstatistical indistinguishabilityunlearned modelvision benchmarks
Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained models, these guarantees do not naturally extend to model outputs when inputs are adversarially perturbed. In particular, slight perturbations of forget samples may still be correctly recognized by the unlearned model