Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention

TL;DR

This paper introduces a novel framework for image-to-image generative model unlearning that treats forgotten data as out-of-distribution, ensuring effective data removal with theoretical guarantees and empirical validation on large datasets.

Contribution

It proposes a decoupling and gradient ascent-based method for unlearning in I2I models, with theoretical guarantees and empirical validation, addressing limitations of previous Gaussian noise approaches.

Findings

Outperforms existing methods on ImageNet-1K and Places365 datasets.

Provides theoretical $(psilon, elta)$-unlearning guarantees.

Achieves comparable performance to retrained models on CIFAR-10.

Abstract

Machine Unlearning allows participants to remove their data from a trained machine learning model in order to preserve their privacy, and security. However, the machine unlearning literature for generative models is rather limited. The literature for image-to-image generative model (I2I model) considers minimizing the distance between Gaussian noise and the output of I2I model for forget samples as machine unlearning. However, we argue that the machine learning model performs fairly well on unseen data i.e., a retrained model will be able to catch generic patterns in the data and hence will not generate an output which is equivalent to Gaussian noise. In this paper, we consider that the model after unlearning should treat forget samples as out-of-distribution (OOD) data, i.e., the unlearned model should no longer recognize or encode the specific patterns found in the forget samples. To achieve this, we propose a framework which decouples the model parameters with gradient ascent, ensuring that forget samples are OOD for unlearned model with theoretical guarantee. We also provide $(\epsilon, \delta)$-unlearning guarantee for model updates with gradient ascent. The unlearned model is further fine-tuned on the remaining samples to maintain its performance. We also propose an attack model to ensure that the unlearned model has effectively removed the influence of forget samples. Extensive empirical evaluation on two large-scale datasets, ImageNet-1K and Places365 highlights the superiority of our approach. To show comparable performance with retrained model, we also show the comparison of a simple AutoEncoder on various baselines on CIFAR-10 dataset.