Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models
This addresses misuse concerns in generative AI by allowing users to remove unwanted concepts, though it is incremental as it builds on continual learning methods.
The paper tackles the problem of harmful content generation in deep generative models by introducing Selective Amnesia, a technique that enables controllable forgetting of specified concepts, achieving effective forgetting across various models including text-to-image diffusion models.
The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by continual learning to selectively forget concepts in pretrained deep generative models. Our method, dubbed Selective Amnesia, enables controllable forgetting where a user can specify how a concept should be forgotten. Selective Amnesia can be applied to conditional variational likelihood models, which encompass a variety of popular deep generative frameworks, including variational autoencoders and large-scale text-to-image diffusion models. Experiments across different models demonstrate that our approach induces forgetting on a variety of concepts, from entire classes in standard datasets to celebrity and nudity prompts in text-to-image models. Our code is publicly available at https://github.com/clear-nus/selective-amnesia.