Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation
This work addresses data privacy and security concerns in federated learning by enabling efficient unlearning, though it appears incremental as it builds on existing knowledge distillation and GAN techniques.
The paper tackles the problem of efficiently removing specific data from federated learning models to enhance privacy, proposing a complete pipeline that includes a federated unlearning approach and an evaluation framework, with experiments demonstrating effectiveness in maintaining model accuracy without storing historical data.
With the increasing importance of data privacy and security, federated unlearning has emerged as a novel research field dedicated to ensuring that federated learning models no longer retain or leak relevant information once specific data has been deleted. In this paper, to the best of our knowledge, we propose the first complete pipeline for federated unlearning, which includes a federated unlearning approach and an evaluation framework. Our proposed federated unlearning approach ensures high efficiency and model accuracy without the need to store historical data.It effectively leverages the knowledge distillation model alongside various optimization mechanisms. Moreover, we propose a framework named Skyeye to visualize the forgetting capacity of federated unlearning models. It utilizes the federated unlearning model as the classifier integrated into a Generative Adversarial Network (GAN). Afterward, both the classifier and discriminator guide the generator in generating samples. Throughout this process, the generator learns from the classifier's knowledge. The generator then visualizes this knowledge through sample generation. Finally, the model's forgetting capability is evaluated based on the relevance between the deleted data and the generated samples. Comprehensive experiments are conducted to illustrate the effectiveness of the proposed federated unlearning approach and the corresponding evaluation framework.