Deep learning classifiers are widely used. Reliable classification confidences are important for safety critical applications, like medical diagnoses or self-driving cars [1]. Out-of-distribution ...

Conclusion This toy dataset might look trivial, but it could act as a magnifying glass: any unfairness introduced by the model stands out because the data themselves are impartial. With this control ...

Abstract: This paper introduces SynTraC, the first public image-based traffic signal control dataset, aimed at bridging the gap between simulated environments and real-world traffic management ...

Abstract: Ensuring the security and resilience of 5G networks requires comprehensive datasets that capture both control and data plane traffic. However, publicly available datasets remain limited, ...