Social networks are a crucial component of the Internet of People (IoP), which represents cutting-edge of Internet of Things (IoT). Predicting a large number of unknown node labels with few known labels is one of the challenging problems in social network analysis. Fortunately, the graph convolutional network (GCN) and subsequent variants have achieved remarkable performance on semi-supervised node classification (SSNC). However, previous works only focus on the case of clean labels and rarely study the problem of SSNC under noisy labels (SSNCNL), which is a more challenging and practical problem in the realm of weakly supervised learning. To cope with the aforementioned challenge, we present a novel dual mutual robust GCN named DMRGCN with inspiration from deep mutual learning and robust learning in the domain of image recognition. Specifically, we first employ two GCNs with different learning abilities to construct network architecture. Then, we define a joint loss function which consists of a weighted combination of supervised loss, mutual loss, and robust loss. Finally, we train the network under the pseudo-siamese network paradigm. Experimental results on three social network benchmark datasets with different levels of noise on labels demonstrate that DMRGCN outperforms the vanilla GCN and several variants on classification accuracy. In particular, under the two conditions of labels without noise and with noise, the node classification accuracy obtained by our proposed DMRGCN can be 3.05% and 6.44% higher than that of the vanilla GCN, respectively.

Device Classification (DC) is one of the critical network management means in the Internet of Things (IoT). Most machine learning-driven DC methods are implemented in two steps: firstly, extracting device features, and then training the classifier. Thus, for the same classifier, the quality of device features plays a decisive role. However, for one thing, these methods usually merely consider device traffic or device attributed features, ignoring the complex relationship between devices in Social IoT. For another thing, these features fed to the classifier are often selected manually without automatic learning. These two factors seriously affect the performance and flexibility of the algorithm. To address the above issues, we propose a novel Graph Contrastive Neural Network-based algorithm for DC dubbed GCNNDC. Specifically, based on the complex relationship between heterogeneous objects in Social IoT and the attribute information of the device itself, we first construct four kinds of homogeneous device-device attributed networks as the input of the neural network. Then, we train a novel GCNN model to learn informative device features in a self-supervised learning fashion. Finally, we leverage the features to train a classifier to complete the DC task. Experimental results on real-world IoT network dataset demonstrate the superiority of GCNNDC.

Industrial Internet of Things (IIoT) and Industry 4.0 empower interrelation among manufacturing processes, industrial machines, and utility services. The time-critical data collected from heterogeneous sensing devices are usually communicated to processing points for analysis and aggregation as the basis of IIoT. The IIoTs’ service quality typically depends on data integrity and accuracy, which could be exploited by injecting malicious events, such as false data injection and data poisoning attacks. Thus, effective anomaly recognition and explanation are critical for ensuring quality services and empowering security administrators to interpret the causal reasoning of prediction decisions and underlying data evidence. This study proposes an autoencoder-based detection framework using convolutional and recurrent networks to discover cyber threats in IIoT networks and explain the model. A two-step sliding window (SW) is applied to learn the latent representations of data features better. Malicious points from the raw time series are transformed into fixed-length series through the first-step SW. Every series is converted into continuous-time-reliant subseries via another smaller SW to learn latent representations of malicious events. Fully connected networks use the extracted temporal and spatial features for the classification and explanation of attack events. The empirical results revealed that this framework effectively extracts features that include contexts of malicious patterns. This demonstrated that the proposed framework is robust in detecting malicious events using multiple evaluation metrics and outperforming the contemporary state-of-the-art methods, indicating its suitability as an operative application method in real-world IIoT-based networks.

Intelligent Transportation Systems (ITS), particularly Autonomous Vehicles (AVs), are susceptible to safety and security concerns that impend people’s lives. Nothing like manually controlled vehicles, the safekeeping of communications and computing constituents of AVs can be threatened using sophisticated hacking techniques, consequently disrupting AVs from the operative usage in our daily life routines. Once manually controlled vehicles are linked to the Internet, so-called the Internet of Vehicles (IoVs), they would be misused by cyberattacks. In this paper, we present a multi-stage intrusion detection framework to identify intrusions from ITSs and produce low rate of false alarms. The proposed framework can automatically distinguish intrusions in real-time. The proposed framework is based on normal state-based and a deep learning-centered bidirectional Long Short Term Memory (LSTM) architecture to efficiently discover intrusions from the fundamental network gateways and communication networks of AVs. The designed framework is evaluated through two benchmark datasources, that is, the UNSWNB-15 datasource for exterior network communications and the car hacking datasource for in-vehicle communications. The outcomes indicated that the proposed framework achieves high performance that outperforms various current state-of-the-art systems with an accuracy rate of 98.88% for the UNSWNB-15 dataset and 99.11% for the car hacking dataset. Besides, the proposed framework is furthermore capable to detect zero-day (concealed) outbreaks from IoVs networks.

Biological network classification is an eminently challenging task in the domain of data mining since the networks contain complex structural information. Conventional biochemical experimental methods and the existing intelligent algorithms still suffer from some limitations such as immense experimental cost and inferior accuracy rate. To solve these problems, in this paper, we propose a novel framework for Biological graph classification named Biogc, which is specifically developed to predict the label of both small-scale and large-scale biological network data flexibly and efficiently. Our framework firstly presents a simplified graph kernel method to capture the structural information of each graph. Then, the obtained informative features are adopted to train different scale biological network data-oriented classifiers to construct the prediction model. Extensive experiments on five benchmark biological network datasets on graph classification task show that the proposed model Biogc outperforms the state-of-the-art methods with an accuracy rate of 98.90% on a larger dataset and 99.32% on a smaller dataset.