Propagation of~Interval Belief Structures and~Imprecise Copulas for~Neural Network Verification

June 29, 2026 Β· Grace Period Β· πŸ› Information Processing and Management of Uncertainty in Knowledge-Based Systems, Jun 2026, Rome, Italy. pp.176-189

⏳ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
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 shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence