Star-based reachability analysis of deep neural networks

DOI10.1007/978-3-030-30942-8_39MaRDI QIDQ6535978zbMATH OpenFDO

Authors Hoang-Dung Tran, Diago Manzanas Lopez, Patrick Musau, Xiao-Dong Yang, Luan Viet Nguyen, Weiming Xiang, Taylor T. Johnson

Publication date 14 March 2024

Full work available at URL https://doi.org/10.1007/978-3-030-30942-8_39

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter
• Analyzing deep neural networks with symbolic propagation: towards higher precision and faster verification
• Reluplex: a calculus for reasoning about deep neural networks
• Abstract neural networks

Cites work

• Reluplex: an efficient SMT solver for verifying deep neural networks
• Safety verification of deep neural networks
• Simulation-equivalent reachability of large linear systems with inputs

Cited in

(15)

• Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training
• Reachability in Simple Neural Networks
• Robustness analysis of continuous-depth models with Lagrangian techniques
• The octatope abstract domain for verification of neural networks
• \textsf{QEBVerif}: quantization error bound verification of neural networks
• LinSyn: synthesizing tight linear bounds for arbitrary neural network activation functions
• Analyzing deep neural networks with symbolic propagation: towards higher precision and faster verification
• Modelling and verifying robotic software that uses neural networks
• Observer-based safety monitoring of nonlinear dynamical systems with neural networks via quadratic constraint approach
• The hexatope and octatope abstract domains for neural network verification
• 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
• ModelStar: reachability analysis-based safety verification of neural networks against model perturbations
• Towards verified and targeted explanations through formal methods

This page was built for publication: Star-based reachability analysis of deep neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6535978)