arXiv AI
Anytime-Valid Runtime Monitoring of Learned Barrier Certificates
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 4
Why Formal Monitors Fail: Attack Distribution Entropy as a Coverage Bound for LTL-Based LLM Agent Safety
arXiv:2608. 01388v1 Announce Type: cross Abstract: Runtime safety monitors based on Linear Temporal Logic (LTL) and finite automata (FSA) are increasingly deployed to intercept unsafe tool-call sequences in LLM agents.
arXiv Machine Learning
Sep 22
Information-Geometric First-Passage Monitoring of Distributional Stability in Stochastic Systems
The paper presents a runtime monitoring framework for stochastic systems that distinguishes normal distributional relaxation from regime changes while limiting false alarms. It combines relative‑entropy dissipation, information geometry, and sequential inference within a bounded first‑passage architecture, employing Gaussian window surrogates, covariance shrinkage, and conformal ranking aggregated by a mixture power‑martingale. Validation on Ornstein–Uhlenbeck dynamics and network intrusion datasets (NSL‑KDD, UNSW‑NB15) shows high detection rates with low false positives, highlighting calibration transport as a key deployment challenge.
arXiv AI
Sep 24
Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination
The paper introduces a finite‑sample probabilistic safety certification framework for black‑box AI decision models used in closed‑loop grid operation. It transforms the AI‑grid evaluation into a binary unsafe outcome under a safety specification and applies exact binomial inference to provide a tight one‑sided upper bound on the unsafe operation probability, using held‑out calibration scenarios. The framework also incorporates physically interpretable sample‑space adversarial attacks to address distribution shifts and is validated through case studies involving 1,000‑agent AI models for grid‑edge flexibility coordination.
arXiv AI
Aug 17
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.
arXiv AI
Jul 16
SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy
arXiv:2607. 13175v1 Announce Type: cross Abstract: Safe reinforcement learning typically enforces safety by bounding expected cumulative costs, a criterion that often fails to detect rare but catastrophic tail events.
arXiv AI
Jun 10
The Distributed Detectability Band Against Marginal-Preserving Attacks
arXiv:2606. 10456v1 Announce Type: cross Abstract: AI-control monitors score individual agent actions to detect misbehavior, but real harm can be distributed across many benign-looking steps, each individually below any per-step alarm.