Verification of Recurrent Neural Networks with Star Reachability
DOI10.1145/3575870.3587128OpenAlexW4375852575MaRDI QIDQ6202081
Tomoya Yamaguchi, Bardh Hoxha, Danil Prokhorov, Sung Woo Choi, Xiao-Dong Yang, Hoang-Dung Tran
Publication date: 21 February 2024
Published in: Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1145/3575870.3587128
Formal languages and automata (68Q45) Specification and verification (program logics, model checking, etc.) (68Q60) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30)
Cites Work
- Scalable polyhedral verification of recurrent neural networks
- Robustness verification of semantic segmentation neural networks using relaxed reachability
- Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter
- A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability
- Reluplex: an efficient SMT solver for verifying deep neural networks
- Simulation-equivalent reachability of large linear systems with inputs
- Verification of deep convolutional neural networks using ImageStars
- Improved geometric path enumeration for verifying ReLU neural networks
- Parsimonious, Simulation Based Verification of Linear Systems
- Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
- Sherlock - A tool for verification of neural network feedback systems
This page was built for publication: Verification of Recurrent Neural Networks with Star Reachability
