TY - CHAP A1 - Hashemi, Vahid A1 - Křetínský, Jan A1 - Rieder, Sabine A1 - Schön, Torsten A1 - Vorhoff, Jan ED - Ábrahám, Erika ED - Abbas, Houssam T1 - Gaussian-Based and Outside-the-Box Runtime Monitoring Join Forces T2 - Runtime Verification: 24th International Conference, Proceedings UR - https://doi.org/10.1007/978-3-031-74234-7_14 Y1 - 2024 UR - https://doi.org/10.1007/978-3-031-74234-7_14 SN - 978-3-031-74234-7 SN - 978-3-031-74233-0 SP - 218 EP - 228 PB - Springer CY - Cham ER - TY - INPR A1 - Hashemi, Vahid A1 - Křetínský, Jan A1 - Rieder, Sabine A1 - Schön, Torsten A1 - Vorhoff, Jan T1 - Gaussian-Based and Outside-the-Box Runtime Monitoring Join Forces N2 - Since neural networks can make wrong predictions even with high confidence, monitoring their behavior at runtime is important, especially in safety-critical domains like autonomous driving. In this paper, we combine ideas from previous monitoring approaches based on observing the activation values of hidden neurons. In particular, we combine the Gaussian-based approach, which observes whether the current value of each monitored neuron is similar to typical values observed during training, and the Outside-the-Box monitor, which creates clusters of the acceptable activation values, and, thus, considers the correlations of the neurons' values. Our experiments evaluate the achieved improvement. UR - https://doi.org/10.48550/arXiv.2410.06051 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2410.06051 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53751 PB - arXiv CY - Ithaca ER -