Few-Shot Unlearning by Model Inversion
We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model. The target dataset is often assumed to be fully identifiable in a standard unlearning scenario. Such a flawless identification, however, is almost impossible if the training dataset is inaccessible at the time of unlearning. Unlike previous approaches requiring a complete set of targets, we consider few-shot unlearning scenario when only a few samples of target data are available. To this end, we formulate the few-shot unlearning problem specifying intentions behind the unlearning request (e.g., purely unlearning, mislabel correction, privacy protection), and we devise a straightforward framework that (i) retrieves a proxy of the training data via model inversion fully exploiting information available in the context of unlearning; (ii) adjusts the proxy according to the unlearning intention; and (iii) updates the model with the adjusted proxy. We demonstrate that our method using only a subset of target data can outperform the state-of-the-art unlearning methods even with a complete indication of target data.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine UnlearningmodelSimilar Papers 제목 키워드 기반
Zero-Shot Machine Unlearning
Modern privacy regulations grant citizens the right to be forgotten by products, services and companies. In case of machine learning (ML) applications, this necessitates deletion of data not only from storage archives bu…
Machine UnlearningTransfer LearningUnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing privacy protection. However, recent research has uncovered critical privacy vulnerabil…
Model Inversion Attack against Federated Unlearning
With the introduction of regulations related to the ``right to be forgotten", federated learning (FL) is facing new privacy compliance challenges. To address these challenges, researchers have proposed federated unlearni…
Federated LearningmodelGenerative Unlearning for Any Identity
Recent advances in generative models trained on large-scale datasets have made it possible to synthesize high-quality samples across various domains. Moreover, the emergence of strong inversion networks enables not only …
Machine UnlearningData-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning
Large language models (LLMs) exhibit powerful capabilities but risk memorizing sensitive personally identifiable information (PII) from their training data, posing significant privacy concerns. While machine unlearning t…