Kolloquiumsvortrag: 28. Januar 2025, Kanwardeep Singh (Betreuer: Muhammad)
AI-driven anomaly detection with ICS protocols in Smart Grid
Motivation:
The swift progression of smart grid technology has transformed contemporary power systems, integrating information technology and industrial control systems (ICS) to boost energy efficiency, dependability, and sustainability. However, this increased connectivity has ushered in new vulnerabilities, rendering smart grids prone to cyber threats that could compromise critical infrastructure. Industrial Control Systems, particularly protocols such as the Manufacturing Message Specification (MMS), are integral to the functioning of smart grids, but they are often not constructed with cybersecurity as a primary consideration. These systems, traditionally secluded, now necessitate stringent security measures to safeguard against malicious attacks and unforeseen operational anomalies. AI-based anomaly detection can pinpoint deviations in protocol behavior that may indicate a cyberattack or operational malfunction. This method not only offers real-time threat detection but also minimizes human intervention, which is vital for mitigating the effects of incidents on critical infrastructure.
Overall Goal:
The solutions for this thesis will focus on development of an AI-based anomaly detection framework for enhancing cybersecurity of Industrial control system (ICS) protocols within smart grid networks. By concentrating on the Manufacturing Message Specification (MMS) protocol, which serves as a vital communication standard in smart grids, this thesis will seek to identify and mitigate potential cyber threats and abnormal network behaviours that could compromise grid reliability and security. The proposed framework utilizes machine learning algorithms to autonomously detect and respond to anomalies in real-time, thereby enhancing the resilience of smart grids against cyber-attacks and operational disruptions. In doing so, this thesis aspires to make a meaningful contribution to the field of industrial cybersecurity by providing scalable, standards-compliant solutions for the protection of critical infrastructure.
Zeit: 10:15 Uhr
Ort: Raum 04.137, Martensstr. 3, Erlangen
oder
Zoom-Meeting beitreten:
https://fau.zoom-x.de/j/68350702053?pwd=UkF3aXY0QUdjeSsyR0tyRWtLQ0hYUT09
Meeting-ID: 683 5070 2053
Kenncode: 647333