The majority of existing anomaly detection methods for multivariate time series are based on
Transformers and Autoencoders owing to their superior capabilities. However, these …

Leveraging labels in a supervised learning framework as prior knowledge to enhance
network anomaly detection has become a trend. Unfortunately, just a few labels are typically …

Anomaly detection is vital in complex distributed systems. However, existing methods did not
take into full account the temporal and spatial characteristics of data from multiple sources in …

Graph anomaly detection primarily relies on shallow learning methods based on feature
engineering and deep learning strategies centred on autoencoder-based reconstruction …

Abstract Heterogeneous Information Networks (HINs) are ubiquitous in the real world, and
discovering anomalies is essential for understanding network semantics through nodes and …

With the widespread use of attribute networks, anomalous node detection on attribute
networks has received increasing attention. By utilizing communities as reference contexts …

Anomaly detection in dynamic networks is an important research task in many application
domains, such as social media, financial fraud, and e-commerce. It aims to identify the …

As a system allowing intra-network devices to automatically communicate over the Internet,
the Internet of Things (IoT) faces increasing popularity in modern applications and security …

Digital Twin (DT) is a promising technology for responding to Industry 4.0 and realizing
comprehensive automation and virtualization. In the Web3. 0-powered 5G/6G era, the …

Attributed networks are prevalent in the current information infrastructure, where node
attributes enhance knowledge discovery. Anomaly detection in attributed networks is …