An adaptive-conformal-plus-incremental-learning safety monitor predicts STL robustness violations with long-run coverage guarantees under arbitrary distribution shift, outperforming conformal and robust-conformal baselines in simulated driving.
Compositional falsification of cyber-physical systems with machine learning components
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios
An adaptive-conformal-plus-incremental-learning safety monitor predicts STL robustness violations with long-run coverage guarantees under arbitrary distribution shift, outperforming conformal and robust-conformal baselines in simulated driving.