POSTER: Advancing Federated Edge Computing with Continual Learning for Secure and Efficient Performance

Federated Learning (FL) and the Internet of Things (IoT) have transformed data processing and analysis, overcoming traditional cloud computing limitations. However, challenges such as catastrophic forgetting in continuous training scenarios arise. To address these, we propose an FL framework that supports continual learning while enhancing system security. We preserve critical knowledge through the incorporation of Knowledge Distillation (KD), addressing the issue of catastrophic forgetting. In addition, we have integrated encryption techniques to secure the updated parameters of clients from potential threats posed by attackers.