arXiv:2609.16373v1 Announce Type: new Abstract: Probabilistic certification of Bayesian neural networks lower-bounds the posterior probability that a model satisfies a verifier-defined safety propert...
arXiv:2608. 16564v1 Announce Type: new Abstract: Machine learning (ML) is a key technology driving innovation today, but ensuring ML safety remains a major challenge for safety-related applications.
The paper introduces a ground‑truth framework for disentangling uncertainty into epistemic and aleatoric components using sample‑conditional pointwise posterior risk. It evaluates current methods, finding that Spectral‑normalized Neural Gaussian Processes and Variational Latent Gaussian Processes best recover the ground‑truth uncertainty, while most methods align more closely with posterior variance and miss predictor bias. The study also explores the entanglement of estimated uncertainties and the impact of modeling choices, providing practical guidance and releasing 13 semi‑synthetic datasets for further validation.
Machine learning (ML) is a key technology driving innovation today, but ensuring ML safety remains a major challenge for safety-related applications. A promising idea is to build proven-in-use arguments from field data, e.
arXiv:2602. 21160v3 Announce Type: replace-cross Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class.
arXiv:2609.13655v1 Announce Type: new Abstract: On evolving graphs, node classifiers must satisfy two key requirements: inductive generalization to newly arriving nodes under distribution shift and c...
arXiv:2410.18321v3 Announce Type: replace Abstract: Confidence calibration matters wherever a classifier's probabilities, not just its labels, are consumed downstream. We study Focal Calibration Loss...
arXiv:2605. 07565v2 Announce Type: replace-cross Abstract: We study Bayesian Optimisation (BO) in settings where the objective function is influenced by uncontrollable environmental contexts governed by an unknown probability distribution.
arXiv:2608. 05995v1 Announce Type: new Abstract: Reliable uncertainty estimates are critical in safety-sensitive applications, where understanding the sources of predictive uncertainty is essential.
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:2606. 02876v1 Announce Type: new Abstract: Randomized smoothing (RS) uses a smoothed classifier to provide architecture-agnostic certificates of $\ell_2$ classification robustness, but its dependence on per-input Monte Carlo (MC) sampling undermines its use in real-time systems.
The paper introduces CertDW, a certified dataset watermark and ownership verification method that remains reliable even under malicious perturbations. By leveraging conformal prediction, it defines two statistical measures—principal probability (PP) and watermark robustness (WR)—to evaluate model stability on benign versus watermarked samples. The authors derive certification conditions linking WR to a PP-based threshold and provide a high‑probability bound on false positives, enabling robust ownership verification when a suspicious model’s WR exceeds the PP values of benign models.