Improved geometric path enumeration for verifying ReLU neural networks

DOI10.1007/978-3-030-53288-8_4MaRDI QIDQ2225077zbMATH OpenOpenAlexFDO

Authors Stanley Bak, Hoang-Dung Tran, Kerianne Hobbs, Taylor T. Johnson

Publication date 4 February 2021

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/978-3-030-53288-8_4

Mathematics Subject Classification ID

Specification and verification (program logics, model checking, etc.) (68Q60) Artificial neural networks and deep learning (68T07)

Recommendations

• Advances in verification of ReLU neural networks
• Scalable polyhedral verification of recurrent neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Robustness verification of ReLU networks via quadratic programming
• Branch and bound for piecewise linear neural network verification
• Neural Network Verification Using Residual Reasoning

Cited in

(21)

• Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter
• Advances in verification of ReLU neural networks
• Static analysis of ReLU neural networks with tropical polyhedra
• Verifying low-dimensional input neural networks via input quantization
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Global optimization of objective functions represented by ReLU networks
• Sparse polynomial optimisation for neural network verification
• Robustness analysis of continuous-depth models with Lagrangian techniques
• Reachability analysis of deep ReLU neural networks using facet-vertex incidence
• Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networks
• The octatope abstract domain for verification of neural networks
• Quantitative Verification for Neural Networks using ProbStars
• Verification of Recurrent Neural Networks with Star Reachability
• Efficient neural network analysis with sum-of-infeasibilities
• The hexatope and octatope abstract domains for neural network verification
• Mechanistic interpretability of ReLU neural networks through piecewise-affine mapping
• Quantitative verification of learning-enabled systems using ProbStar reachability
• ProbStar temporal logic for verifying complex behaviors of learning-enabled systems
• Reachability analysis of recurrent neural networks
• Counterexample-guided abstraction refinement for star-based neural network verification
• Robustness verification of semantic segmentation neural networks using relaxed reachability

This page was built for publication: Improved geometric path enumeration for verifying ReLU neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2225077)