D3FU : Data-Free Distillation Driven Federated Unlearning for Service-Oriented Computing

Edge Computing (EC) enables deep neural network training on distributed data, yet it raises significant privacy concerns, particularly under regulations enforcing the “right to be forgotten”. Federated Unlearning (FU) offers a solution by allowing targeted data unlearning without the need for retraining. In Service-Oriented Computing (SOC) systems, where services are composed dynamically and data flows across multiple decentralized nodes, deploying FU introduces additional challenges. Specifically, the lack of direct access to raw data within loosely coupled services, along with the high communication cost required for coordination among distributed components, significantly hinders effective unlearning. Therefore, we propose D3FU, an efficient service-compatible framework that leverages data-free knowledge distillation to achieve self-contained FU. This framework employs local unlearning through Projected Gradient Descent (PGD), which may initially degrade model performance. To mitigate the resulting bias, we integrate Model-Agnostic Meta-Learning (MAML) techniques to generate task-relevant pseudo-samples, thereby enabling data-free distillation and correcting the gradient updates of the local unlearned model. This process effectively restores model performance while ensuring accurate unlearning. Our experimental results, including evaluations of backdoor attacks, demonstrate that D3FU achieves unlearning effects comparable to retraining from scratch, with a maximum reduction in communication cost by up to 32 times.