Gaussian-Based and Outside-the-Box Runtime Monitoring Join Forces
| Authors | |
|---|---|
| Year of publication | 2024 |
| Type | Article in Proceedings |
| Conference | RV 2024, 24th International Conference on Runtime Verification |
| MU Faculty or unit | |
| Citation | |
| Doi | http://dx.doi.org/10.1007/978-3-031-74234-7_14 |
| Keywords | Runtime Monitoring; Neural Networks; Out-of-Model-Scope Detection |
| Description | 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. |
| Related projects: |