Nan Sun

Intrusion Detection Systems (IDSs) have evolved to safeguard networks and systems from cyber attacks. Anomaly-based Intrusion Detection Systems (A-IDS) have been commonly employed to detect known and unknown anomalies. However, conventional anomaly detection approaches encounter substantial challenges when dealing with large-scale and heterogeneous data sources. These challenges include high False Positive Rates (FPRs), imbalanced data behavior, complex data handling, resource constraints, limited interpretability, and difficulties with encrypted networks. This survey reviews 60 technical papers (2019–2025) on graph-based anomaly detection (GBAD) approaches, highlighting their ability to address these challenges by utilizing the inherent structure of graphs to capture and analyze network connectivity patterns. Our analysis reveals that 32 studies (53%) employ two-stage methods while 28 (47%) use end-to-end approaches. Among the end-to-end methods, GNN-based techniques dominate, accounting for 18 of the 28 papers. We present a phased graph-based anomaly detection methodology for intrusion detection. This includes phases of data capturing, graph construction, graph pre-processing, anomaly detection, and post-detection analysis. Furthermore, we examine the evaluation methods and datasets employed in GBAD research and provide an analysis of the types of attacks identified by these methods. The most utilized datasets include CICIDS, UNSW-NB15, and DARPA, while precision, recall, and F1-score are employed in over 85% of studies. Lastly, we outline the key challenges and future directions that require significant research efforts in this area, and we offer some recommendations to address them.

Intrusion Detection Systems (IDSs) have evolved to safeguard networks and systems from cyber attacks. Anomaly-based Intrusion Detection Systems (A-IDS) have been commonly employed to detect known and unknown anomalies. However, conventional anomaly detection approaches encounter substantial challenges when dealing with complex, large-scale, and heterogeneous data sources. These challenges include high False Positive Rates (FPRs), imbalanced data behavior, complex data handling, resource constraints, limited interpretability, and difficulties with encrypted networks. This survey reviews Graph-based Anomaly Detection (GBAD) approaches, highlighting their ability to address these challenges by utilizing the inherent structure of graphs to capture and analyze network connectivity patterns. GBAD approaches offer flexibility for handling diverse data types, scalability to analyze large datasets, robustness detection capabilities, and enhanced interpretability through visualizations. We present a phased graph-based anomaly detection methodology for intrusion detection. This includes phases of data capturing, graph construction, graph pre-processing, anomaly detection, and post-detection analysis. Furthermore, we examine the evaluation methods and datasets employed in GBAD research and provide an analysis of the types of attacks identified by these methods. Lastly, we outline the key challenges and future directions that require significant research efforts in this area and offer some recommendations to address them.

The accurate prediction of the pavement structural modulus is crucial for maintenance planning and life-cycle assessment. While recent deep learning models have improved predictive accuracy using Falling Weight Deflectometer data, challenges remain in effectively structuring time-series inputs and ensuring robustness against noise measurement. This paper presents an integrated framework that combines systematic time-step modeling with perturbation-based robustness evaluation. Five distinct input sequencing strategies (Plan A through Plan E) were developed to investigate the impact of temporal structure on model performance. A hybrid Wide & Deep ResRNN architecture incorporating SimpleRNN, GRU, and LSTM components was designed to jointly predict four-layer moduli. To simulate real-world sensor uncertainty, Gaussian noise with ±3% variance was injected into inputs, allowing the Monte-Carlo-style estimation of confidence intervals. Experimental results revealed that time-step design plays a critical role in both prediction accuracy and robustness, with Plan D consistently achieving the best balance between accuracy and stability. These findings offer a practical and generalizable approach for deploying deep sequence models in pavement modulus prediction tasks, particularly under uncertain field conditions.

Accurate forecasting of tropical cyclone (TC) tracks is critical for disaster preparedness and risk mitigation. While traditional numerical weather prediction (NWP) systems have long served as the backbone of operational forecasting, they face limitations in computational cost and sensitivity to initial conditions. In recent years, deep learning (DL) has emerged as a promising alternative, offering data-driven modeling capabilities for capturing nonlinear spatiotemporal patterns. This paper presents a comprehensive review of DL-based approaches for TC track forecasting. We categorize all DL-based TC tracking models according to the architecture, including recurrent neural networks (RNNs), convolutional neural networks (CNNs), Transformers, graph neural networks (GNNs), generative models, and Fourier-based operators. To enable rigorous performance comparison, we introduce a Unified Geodesic Distance Error (UGDE) metric that standardizes evaluation across diverse studies and lead times. Based on this metric, we conduct a critical comparison of state-of-the-art models and identify key insights into their relative strengths, limitations, and suitable application scenarios. Building on this framework, we conduct a critical cross-model analysis that reveals key trends, performance disparities, and architectural tradeoffs. Our analysis also highlights several persistent challenges, such as long-term forecast degradation, limited physical integration, and generalization to extreme events, pointing toward future directions for developing more robust and operationally viable DL models for TC track forecasting. To support reproducibility and facilitate standardized evaluation, we release an open-source UGDE conversion tool on GitHub.