IEC 60870-5-104 (IEC-104) is widely deployed in SCADA-based power systems to transport telecontrol messages over TCP/IP. While improving interoperability, this connectivity expands the cyber attack surface and enables threats targeting both availability and integrity. This paper presents a comparative evaluation of supervised machine learning (ML) models for intrusion detection on IEC-104 communication using a laboratory SCADA testbed and labeled datasets derived from packet captures. Three representative scenarios are considered: SYN Flood targeting TCP port 2404 (Layer 4 denial-of-service), APDU Flood at the application layer (Layer 7 denial-ofservice), and Control Command Injection Attack (CCIA) via man-in-the-middle command manipulation (integrity attack). Features are extracted using TShark and combine transport/network indicators with IEC-104-aware attributes (APDU length, I/S/U frame type, ASDU Type ID, Cause of Transmission, and IOA), consistent with the importance of protocol-aware inspection in IEC-104 IDS research. Evaluation uses stratified random record-level splitting for SYN Flood due to limited sample size and time-based hold-out validation for the combined APDU+CCIA dataset to assess temporal generalization. Results show that SYN Flood is detected reliably with tuned SVM achieving 85.57% accuracy and perfect recall (100%). Under time-based validation on APDU+CCIA, overall performance remains high (accuracy 98.54%-99.39%) and APDU Flood detection is near-perfect (accuracy 99.02%-99.87%), whereas CCIA detection accuracy $(\mathbf{5 2. 3 0 \% - 6 0. 6 2 \%})$ remains substantially lower, indicating the need for richer semantic and temporal features for integrity-focused anomalies in IEC-104 traffic.
Sofyan Asyzauri, A. Affandi, P. H. Mukti et al.· International Seminar on Int...· 0 citations
Conventional optimization still poses a significant challenge when it comes to producing the designs required for modern communication technologies. Previous studies have mainly focused on effectiveness and computational efficiency, but have not sufficiently addressed robustness, an essential factor in surrogate-assisted optimization for Microstrip Antenna (MSA) design. Unlike existing surrogate-assisted optimization approaches, this study explicitly incorporates robustness analysis, statistical validation, and sensitivity-driven interpretability into a unified multi-parameter optimization framework. This framework is referred to as a Robustness-Driven Surrogate Optimization Framework (RDSOF). A regression-based Machine Learning (ML) approach using Extreme Gradient Boosting (XGBoost) is employed to model the relationship among 11 geometric input parameters and key antenna performance metrics, including the input reflection coefficient (S₁₁), Bandwidth (BW), and Voltage Standing Wave Ratio (VSWR). The model is trained on a simulation-generated dataset comprising 1,920 samples generated from diverse geometric configurations. The surrogate model is evaluated inside the optimization loop under four optimization scenarios. Following this, robustness and sensitivity analyses are conducted to assess the reliability and influence of the design parameters. The outcomes indicate that the Differential Evolution (DE) approach achieves superior Electromagnetic (EM) performance, particularly in minimizing S₁₁. However, Particle Swarm Optimization (PSO) demonstrates greater stability, as shown by the relatively small difference in fitness standard deviation among its default and tuned configurations. Overall, the proposed RDSOF demonstrates capability in balancing exploration and exploitation while emphasizing robustness and computational efficiency for Rectangular Microstrip Antenna (RMSA) design.
Agusriandi, A. Affandi, Eko Setijadi· Engineering, Technology &...· 0 citations