π
π
The Cartographer
Propagation of~Interval Belief Structures and~Imprecise Copulas for~Neural Network Verification
June 29, 2026 Β· Grace Period Β· π Information Processing and Management of Uncertainty in Knowledge-Based Systems, Jun 2026, Rome, Italy. pp.176-189
Authors
Francesc Pifarre-Esquerda, Eric Goubault, Sylvie Putot
arXiv ID
2606.30105
Category
cs.AI: Artificial Intelligence
Cross-listed
cs.LO,
math.PR
Citations
0
Venue
Information Processing and Management of Uncertainty in Knowledge-Based Systems, Jun 2026, Rome, Italy. pp.176-189
Abstract
Quantitative verification of neural networks requires reasoning about probabilities under substantial uncertainty in both input distributions and their dependence structure. In realistic settings, this information is often only partially specified, and assuming precise probabilistic models can lead to unreliable results. We propose a sound framework for quantitative verification under imprecise probabilistic information, combining interval belief structures to represent marginal uncertainty with imprecise copulas to model uncertain dependence. We develop a propagation method for imprecisely coupled interval belief structures through feed-forward neural networks. Using mixed imprecise copula volumes, we derive sound push-forward constructions through affine transformations and activation functions. The resulting output can provide guaranteed lower and upper bounds on probabilistic safety properties, valid for all probability models compatible with the specified imprecise inputs.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Artificial Intelligence
R.I.P.
π»
Ghosted
Explanation in Artificial Intelligence: Insights from the Social Sciences
R.I.P.
π»
Ghosted
Federated Machine Learning: Concept and Applications
R.I.P.
π»
Ghosted
Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR
R.I.P.
π»
Ghosted
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
R.I.P.
π»
Ghosted