Our tool enables companies to easily test the robustness of their AI models
Robuscope allows industrial companies, universities and other scientific institutions to test the robustness of the results of their AI model. The new platform uses metrics for uncertainty and robustness quantification to assess the reliability of the tested AI models. The online tool of Fraunhofer IKS provides detailed information on how the tested AI models can be optimized and thus be made safer.
What causes undependable AI models?
-
Overconfidence in their predictions
-
Unpredictable behaviour for semantically unknown inputs
-
Limited explainability of the predictions
-
Susceptibility regarding attacks
-
Impede the use of AI models in production systems
What features does the tool offer?
-
Quick, comprehensible, and understandable robustness analysis
-
Suggestions for improvements
-
Support for different ML models and applications
-
Confidental handling of client data
-
Facilitate the use of AI models in production systems
Get in touch