Research: Evaluating the Detection and Mitigation of False-Data-Injection Attacks in Sm...

Research question: How effective are current anomaly detection and mitigation strategies against false-data-injection attacks on smart-grid SCADA systems, and how can they be improved?

Background and Motivation: The increasing integration of digital control and communication networks into power systems has made smart-grid SCADA (Supervisory Control and Data Acquisition) systems vital for grid reliability and efficiency. However, these advancements have also exposed critical infrastructures to sophisticated cyber threats, notably false-data-injection (FDI) attacks that can compromise grid operations without immediate detection.

Research Gap: While several anomaly detection and mitigation methods have been proposed, the evolving nature of FDI attacks and the complexity of SCADA architectures challenge the robustness of existing defenses. There is a need for a systematic evaluation of these methods to identify vulnerabilities and propose enhancements tailored to realistic smart-grid environments.

Approach and Expected Contribution: This project will conduct a comprehensive literature review, identify leading detection and mitigation approaches, and evaluate their performance using simulated FDI attacks on benchmark SCADA datasets and open-source grid simulators. The study will analyze detection accuracy, false positive rates, and response times, and propose improvements or hybrid strategies to enhance resilience.

Significance: Strengthening the cybersecurity of smart-grid SCADA systems is essential for maintaining secure, reliable, and resilient power delivery in the face of emerging cyber threats. The findings will inform both academic research and practical policy for critical infrastructure protection.