Analyzing deep neural networks with symbolic propagation: towards higher precision and faster verification

DOI10.1007/978-3-030-32304-2_15zbMATH Open1539.68173MaRDI QIDQ6536294FDOQ6536294

Authors: Jian-Lin Li, Jiangchao Liu, Peng-fei Yang, Liqian Chen, Xiaowei Huang, Lijun Zhang 

Publication date: 19 April 2024

Recommendations

• Enhancing robustness verification for deep neural networks via symbolic propagation
• Reluplex: a calculus for reasoning about deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Abstract neural networks
• Star-based reachability analysis of deep neural networks

Mathematics Subject Classification ID

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

Cites Work

• Safe bounds in linear and mixed-integer linear programming
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Formal verification of piece-wise linear feed-forward neural networks

Cited In (4)

• \textsc{OccRob}: efficient SMT-based occlusion robustness verification of deep neural networks
• \textsf{QEBVerif}: quantization error bound verification of neural networks
• LinSyn: synthesizing tight linear bounds for arbitrary neural network activation functions
• Star-based reachability analysis of deep neural networks

This page was built for publication: Analyzing deep neural networks with symbolic propagation: towards higher precision and faster verification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6536294)