Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving the data isolation problem faced by centralized GNNs in data-sensitive scenarios. Despite the plethora of prior work on inference attacks against centralized GNNs, the vulnerability of FedGNNs to inference attacks has not yet been widely explored. It is still unclear whether the privacy leakage risks of centralized GNNs will also be introduced in FedGNNs. To bridge this gap, we present PIAFGNN, the first property inference attack (PIA) against FedGNNs. Compared with prior works on centralized GNNs, in PIAFGNN, the attacker can only obtain the global embedding gradient distributed by the central server. The attacker converts the task of stealing the target user’s local embeddings into a regression problem, using a regression model to generate the target graph node embeddings. By training shadow models and property classifiers, the attacker can infer the basic property information within the target graph that is of interest. Experiments on three benchmark graph datasets demonstrate that PIAFGNN achieves attack accuracy of over 70% in most cases, even approaching the attack accuracy of inference attacks against centralized GNNs in some instances, which is much higher than the attack accuracy of the random guessing method. Furthermore, we observe that common defense mechanisms cannot mitigate our attack without affecting the model’s performance on mainly classification tasks.

We consider the extrema estimation problem in large-scale radio-frequency identification (RFID) systems, where there are thousands of tags and each tag contains a finite value. The objective is to design an extrema estimation protocol with the minimum execution time. Because the standard binary search protocol wastes much time due to interframe overhead, we propose a parameterized protocol and treat the number of slots in a frame as an unknown parameter. We formulate the problem and show how to find the best parameter to minimize the worst-case execution time. Finally, we propose two rules to further reduce the execution time. The first is to find and remove redundant frames. The second is to concatenate a frame from minimum value estimation with a frame from maximum value estimation to reduce the total number of frames. Simulations show that, in a typical scenario, the proposed protocol reduces execution time by 79% compared with the standard binary search protocol.