Members of the CyberFactory#1 project consortium participated in the Machine Learning in Certified Systems Workshop organised by the DEEL project. Ana Pereira from the University of Applied Sciences Berlin (HTW) presented a poster on “Safety Hazards Analysis and Mitigation Strategies for Machine Learning-Based Safety-Critical Systems”.
Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS). As a consequence, the safety of machine learning became a focus area for research in recent years. Applying a classic technique of safety engineering, our work provides a methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and that could compromise the safe operation of ML-based CPS. The comprehensive analysis presented here intends to be used as a basis for holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the use of ML-based control systems in highly safety-critical applications and their certification.
The poster was created by Ana Pereira and Carsten Thomas from the University of Applied Sciences Berlin (HTW).
You can download the poster here.