AI Defenders: Machine learning driven anomaly detection in critical infrastructures
Nebebe B, Kröckel P, Yatagha R, Edeh N, Waedt K (2024)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2024
Publisher: Springer Verlag GI LNI Proceedings 2024
Conference Proceedings Title: 9th IACS WS'24: 9th GI/ACM Workshop on Industrial Automation and Control Systems 2024
Event location: Wiesbaden, Deutschland, Hochschule RheinMain Wiesbaden
Abstract
In recent years, the integration of Artificial Intelligence (AI) across various industries has highlighted its significant advantages, from routine applications to critical sectors such as healthcare and nuclear power plants. AI's capacity to detect and respond faster than humans make it a pivotal component in enhancing the resilience of our infrastructures against potential attacks. One of the key applications of AI is in anomaly detection, where its ability to identify patterns invisible to the human eye is particularly valuable. Anomalies are data points that deviate significantly from the expected pattern and indicate irregularities or potential threats within a system. Anomaly detection is crucial for maintaining the integrity and continuous operation of critical infrastructures. Delayed responses to anomalies in these systems can lead to severe consequences, including operational downtime, financial losses, data breaches, and safety hazards. Ensuring robust anomaly detection mechanisms within a company's infrastructure is therefore vital for mitigating risks and sustaining uninterrupted operations.
Authors with CRIS profile
How to cite
APA:
Nebebe, B., Kröckel, P., Yatagha, R., Edeh, N., & Waedt, K. (2024). AI Defenders: Machine learning driven anomaly detection in critical infrastructures. In 9th IACS WS'24: 9th GI/ACM Workshop on Industrial Automation and Control Systems 2024. Wiesbaden, Deutschland, Hochschule RheinMain Wiesbaden, DE: Springer Verlag GI LNI Proceedings 2024.
MLA:
Nebebe, Betelhem, et al. "AI Defenders: Machine learning driven anomaly detection in critical infrastructures." Proceedings of the Informatik Festival 2024, 9th IACS WS'24, Wiesbaden, Deutschland, Hochschule RheinMain Wiesbaden Springer Verlag GI LNI Proceedings 2024, 2024.
BibTeX: Download