Abstract Advanced wireless communication is important in distribution systems for sharing information among Internet of Things (IoT) edges. Artificial intelligence (AI) analyzed the generated IoT data to make these decisions, ensuring efficient and effective operations. These technologies face significant security challenges, such as eavesdropping and adversarial attacks. Recent studies addressed this issue by using clustering analysis (CA) to uncover hidden patterns to provide AI models with clear interpretations. The high volume of overlapped samples in IoT data affects partitioning, interpretation, and reliability of CAs. Recent CA models have integrated machine learning techniques to address these issues, but struggle in the limited resources of IoT environments. These challenges are addressed by proposing a novel unsupervised lightweight distance clustering (DC) model based on data separation (). raises the tension between samples using cannot‐link relations to separate the overlap, thus DC provides the interpretations. The optimal time and space complexity enables DC‐ to be implemented on on‐edge computing, reducing data transmission overhead, and improving the robustness of the AI‐IoT application. Extensive experiments were conducted across various datasets under different circumstances. The results show that the data separated by improved the efficiency of the proposed solution, with DC outperforming the baseline model.

Graph de-anonymization is a technique used to reveal connections between entities in anonymized graphs, which is crucial in detecting malicious activities, network analysis, social network analysis, and more. Despite its paramount importance, conventional methods often grapple with inefficiencies and challenges tied to obtaining accurate query graph data. This paper introduces a neural-based inexact graph de-anonymization, which comprises an embedding phase, a comparison phase, and a matching procedure. The embedding phase uses a graph convolutional network to generate embedding vectors for both the query and anonymized graphs. The comparison phase uses a neural tensor network to ascertain node resemblances. The matching procedure employs a refined greedy algorithm to discern optimal node pairings. Additionally, we comprehensively evaluate its performance via well-conducted experiments on various real datasets. The results demonstrate the effectiveness of our proposed approach in enhancing the efficiency and performance of graph de-anonymization through the use of graph embedding vectors.

As one of the most promising machine learning frameworks emerging in recent years, Federated learning (FL) has received lots of attention. The main idea of centralized FL is to train a global model by aggregating local model parameters and maintain the private data of users locally. However, recent studies have shown that traditional centralized federated learning is vulnerable to various attacks, such as gradient attacks, where a malicious server collects local model gradients and uses them to recover the private data stored on the client. In this paper, we propose a DEcentralized FEderated learning Against aTtacks (DEFEAT) framework and use it to defend the gradient attack. The decentralized structure adopted by this paper uses a peer-to-peer network to transmit, aggregate, and update local models. In DEFEAT, the participating clients only need to communicate with their single-hop neighbors to learn the global model, in which the model accuracy and communication cost during the training process of DEFEAT are well balanced. Through a series of experiments and detailed case studies on real datasets, we evauate the excellent model performance of DEFEAT and the privacy preservation capability against gradient attacks.

As a research hotspot for graph mining technology, Graph Convolutional Networks (GCN) have achieved remarkable performance in the fields of wireless networks, Internet of Things, and edge computing. However, recent studies have shown that GCN is vulnerable to adversarial attack; that is, even imperceptible intentional perturbations on graph structure or node attributes can significantly change classification results. This paper proposes a novel graph convolutional network, Pairwise Gaussian Graph Convolutional Networks (PGGCN), in which a pairwise architecture is designed for GCN model construction and training. This elegant design enables PGGCN to mitigate the effects of adversarial attack and thus improve model robustness while guaranteeing classification accuracy. The performance of PGGCN is validated through extensive experimental results, which confirm that PGGCN can effectively improve the robustness of GCN while ensuring classification accuracy.