배운 장벽 인증서의 언제든지 유효한 Runtime Monitoring of Learned Barrier Certificates / Anytime-Valid Runtime Monitoring of Learned Barrier Certificates (2026) (Korean)

학습된 장벽 인증서는 스토카스틱 시스템의 안전을 확립하기위한 원칙적인 데이터 메커니즘을 제공하지만 기본적인 역학이 훈련에 사용되는 것과 다를 때 배포하는 동안 유효성은 악화 될 수 있습니다. 우리는 학습 된 장벽 인증서를 관찰하는 언제든지 유효한 실행 시간 모니터를 제안합니다. 모니터는 배포 된 장벽 상태에 대한 통계적 지원의 손실을 감지하기위한 것입니다. 그것은 자체적으로 불안정한 입구 또는 후속 개입의 안전을 보장하지 않습니다. 구체적으로, 조건부 장벽 - 드라이브 조건은 에피소드 방식으로 학습 된 장벽 가수 테스트로 형성되며 관찰 된 장벽 증가는 비정상적인 테스트 슈퍼마트링에 변

Abstract

Learned barrier certificates provide a principled mechanism for establishing safety of stochastic systems, but their validity may deteriorate during deployment when the underlying dynamics differ from those used for training. We propose an anytime-valid runtime monitor that audits a learned barrier certificate using observed closed-loop trajectories. The monitor is intended to detect loss of statistical support for the deployed barrier condition; it does not by itself guarantee detection before unsafe entry or safety of a subsequent intervention. Specifically, the conditional barrier-drift condition is formulated as an episode-wise sequential hypothesis test, and observed barrier increments are transformed into a nonnegative test supermartingale, yielding finite-sample false-alarm control under arbitrary stopping times. Inspired by finite-horizon safety verification, we further introduce a deterministic temporal shaping of the monitoring boundary, making the monitor more conservative early in a prescribed deployment horizon while preserving anytime-validity. The monitor is designed to detect statistical evidence that the safety certificate is no longer consistent with the observed dynamics, rather than to predict unsafe entry. To assess the monitor empirically, we evaluate empirical alarm behavior under valid and invalid certificates. Code and data are available at https://github.com/FormalCert-AI/runtime-barrier-monitor.

Topics: Certificate, Computer science, Software deployment, ALARM, Audit, Control (management)

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27726, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt