In the era emphasizing the privacy of personal data, verifiable federated learning has garnered significant attention as a machine learning approach to safeguard user privacy while simultaneously validating aggregated result. However, there are some unresolved issues when deploying verifiable federated learning in edge computing. Due to the constraint resources, edge computing demands cost saving measurements in model training such as model pruning. Unfortunately, there is currently no protocol capable of enabling users to verify pruning results. Therefore, in this paper, we introduce PrVFL, a verifiable federated learning framework that supports model pruning verification and heterogeneous edge computing. In this scheme, we innovatively utilize zero-knowledge range proof protocol to achieve pruning result verification. Additionally, we first propose a heterogeneous delayed verification scheme supporting the validation of aggregated result for pruned heterogeneous edge models. Addressing the prevalent scenario of performance-heterogeneous edge clients, our scheme empowers each edge user to autonomously choose the desired pruning ratio for each training round based on their specific performance. By employing a global residual model, we ensure that every parameter has an opportunity for training. The extensive experimental results demonstrate the practical performance of our proposed scheme.

Energy consumption is a first-order concern for battery-driven smartphones. To maximize battery life, Android employs an aggressive Power Management policy. The WakeLock mechanism is the key feature of Android Power Management, which allows application developers to explicitly prevent the critical resources including CPU, screen and keyboard from entering sleep state using WakeLock API. If abused, the application can drain the battery at a fast rate even when the application is not running. Unfortunately, the current programming environment of Android does not offer a reliable facility to identify Wakelock bugs in programs. To solve this problem, we have implemented a novel tool called WLCleaner that can detect WakeLock bugs and automatically handle it at runtime to minimize the power waste for users. We evaluate WLCleaner with real-world applications running on two Android smartphones, and the results show that when WakeLock bugs are removed by WLCleaner, the energy consumption at screen-off time is reduced by half.