Certified Uncertainty Propagation in One-Shot Federated Bayesian Models via Posterior Event Transport

• URL: http://arxiv.org/abs/2609.16373v1
• Date: Mon, 14 Sep 2026 21:34:32 GMT
• Title: Certified Uncertainty Propagation in One-Shot Federated Bayesian Models via Posterior Event Transport
• Abstract summary: This paper develops a deployment-consistent certification framework for Federated Averaging (FedAvg)<n>Experiments on MNIST and Fashion-MNIST under label-Dirichlet show that the transported FedAvg certificate ranges from 22.51% to 46.89%.<n>Results show that predictive accuracy and certifiable safety do not necessarily follow the same trend, and that global posterior constructions can exhibit distinct certification behavior across architectures.
• Score: 4.619828919345113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Probabilistic certification of Bayesian neural networks lower-bounds the posterior probability that a model satisfies a verifier-defined safety property. In one-shot federated Bayesian learning, however, the deployed model is obtained by aggregating parameters drawn from client-specific posterior distributions, so local certificates do not directly guarantee safety of the aggregated model. This paper develops a deployment-consistent certification framework by propagating local posterior events through the deployment aggregation rule, with an exact geometric characterization for Federated Averaging (FedAvg). Each client constructs disjoint hyper-rectangular regions in parameter space and computes their probability masses. The server forms Cartesian products of these regions, maps them through the deployment rule, and retains a product event only when its aggregation image is verified to satisfy the safety property. Under independent client posteriors, each product-event probability factorizes into local masses, and summing verified disjoint events yields a lower bound on safety probability of the deployed model. For FedAvg with nonnegative aggregation coefficients, the image of a Cartesian product of axis-aligned hyper-rectangles is exactly a weighted hyper-rectangle, introducing no set over-approximation. We distinguish the proposed transported-event certificate from direct certification under posterior distributions induced by FedAvg and Product-of-Gaussians aggregation. Experiments on MNIST and Fashion-MNIST under label-Dirichlet heterogeneity show that the transported FedAvg certificate ranges from 22.51% to 46.89%, while direct global certificates range from 72.05% to 91.39%. Results show that predictive accuracy and certifiable safety do not necessarily follow the same trend, and that global posterior constructions can exhibit distinct certification behavior across architectures.

Related papers

• A distribution-free certification framework for trustworthy crash-severity prediction [1.089614199781423]
  We develop a certification layer that wraps any severity model unmodified.<n>On 5.2 million Texas records across seven base models spanning four decades, the layer attaches identical validity.<n>The framework is released as an open-source package with theorem-level tests.
  arXiv  Detail & Related papers  (2026-09-10T14:20:08Z)
• Certifying Plans under Model Mismatch: A Trilemma for Reachability from Scarce Data [5.455772242709494]
  Sim-to-real policies are designed under nominal dynamics, but target-system trials may yield only a few isolated one-step transitions.<n>We study pre-execution certification of a fixed control sequence, such as an action chunk produced by a learned policy.
  arXiv  Detail & Related papers  (2026-08-03T16:28:26Z)
• Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers [1.9839136494100942]
  Guardrails defend production language models against harmful behavior, but they provide no formal guarantees.<n>We propose two constructions of such regions: SVD-aligned hyper-rectangles and Gaussian Mixture Models.<n>Applying this framework to three author-trained Guardrails on the toxicity domain, every hyper-rectangle configuration returns SAT.<n>While GPT-2 and Llama-3.1-8B maintain robust coverage of 90% and 80% across varying boundaries, BERT's safety guarantees prove uniquely volatile.
  arXiv  Detail & Related papers  (2026-05-11T17:41:38Z)
• Towards Generalizable Deepfake Detection via Real Distribution Bias Correction [62.89674593681203]
  We introduce the Real Distribution Bias Correction (RDBC) framework, which consists of two key components.<n>RDBC achieves state-of-the-art performance in both in-domain and cross-domain deepfake detection.
  arXiv  Detail & Related papers  (2026-03-14T16:11:00Z)
• Natural Geometry of Robust Data Attribution: From Convex Models to Deep Networks [9.553350856191743]
  We present a unified framework for robust attribution that extends from convex models to deep networks.<n>For convex settings, we derive Wasserstein-Robust Influence Functions (W-RIF) with provable coverage guarantees.<n>For deep networks, we demonstrate that Euclidean certification is rendered vacuous by spectral amplification.
  arXiv  Detail & Related papers  (2025-12-09T20:40:27Z)
• Federated Conditional Conformal Prediction via Generative Models [12.463514743585515]
  Conformal Prediction (CP) provides distribution-free uncertainty quantification.<n>Fed Conditional Conformal Prediction (Fed-CCP) aims for conditional coverage that adapts to local data heterogeneity.<n> Experiments on real datasets demonstrate that Fed-CCP achieves more adaptive prediction sets.
  arXiv  Detail & Related papers  (2025-10-15T08:38:38Z)
• Perfectly-Private Analog Secure Aggregation in Federated Learning [51.61616734974475]
  In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model.<n>In this paper, a novel secure parameter aggregation method is proposed that employs the torus rather than a finite field.
  arXiv  Detail & Related papers  (2025-09-10T15:22:40Z)
• Localized Randomized Smoothing for Collective Robustness Certification [60.83383487495282]
  We propose a more general collective robustness certificate for all types of models. We show that this approach is beneficial for the larger class of softly local models. The certificate is based on our novel localized randomized smoothing approach.
  arXiv  Detail & Related papers  (2022-10-28T14:10:24Z)
• Certifying Model Accuracy under Distribution Shifts [151.67113334248464]
  We present provable robustness guarantees on the accuracy of a model under bounded Wasserstein shifts of the data distribution. We show that a simple procedure that randomizes the input of the model within a transformation space is provably robust to distributional shifts under the transformation.
  arXiv  Detail & Related papers  (2022-01-28T22:03:50Z)
• CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks [58.29502185344086]
  In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks. It is important to provide provable guarantees for deep learning models against semantically meaningful input transformations. We propose a new universal probabilistic certification approach based on Chernoff-Cramer bounds.
  arXiv  Detail & Related papers  (2021-09-22T12:46:04Z)
• Data Dependent Randomized Smoothing [127.34833801660233]
  We show that our data dependent framework can be seamlessly incorporated into 3 randomized smoothing approaches. We get 9% and 6% improvement over the certified accuracy of the strongest baseline for a radius of 0.5 on CIFAR10 and ImageNet.
  arXiv  Detail & Related papers  (2020-12-08T10:53:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.