A game-based approximate verification of deep neural networks with provable guarantees
From MaRDI portal
Publication:2286751
DOI10.1016/j.tcs.2019.05.046zbMath1436.68199arXiv1807.03571OpenAlexW2869036160MaRDI QIDQ2286751
Publication date: 22 January 2020
Published in: Theoretical Computer Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1807.03571
Artificial neural networks and deep learning (68T07) Applications of statistical and quantum mechanics to economics (econophysics) (91B80) Pattern recognition, speech recognition (68T10) Specification and verification (program logics, model checking, etc.) (68Q60)
Related Items (11)
Robustness verification of semantic segmentation neural networks using relaxed reachability ⋮ Generalizing universal adversarial perturbations for deep neural networks ⋮ Reachability analysis of deep ReLU neural networks using facet-vertex incidence ⋮ Bridging formal methods and machine learning with model checking and global optimisation ⋮ Bicriteria algorithms to balance coverage and cost in team formation under online model ⋮ Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper). ⋮ A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability ⋮ Improving neural network verification through spurious region guided refinement ⋮ Enhancing robustness verification for deep neural networks via symbolic propagation ⋮ Bicriteria streaming algorithms to balance gain and cost with cardinality constraint ⋮ Constructing the basis path set by eliminating the path dependency
Uses Software
Cites Work
This page was built for publication: A game-based approximate verification of deep neural networks with provable guarantees