Enhancing robustness verification for deep neural networks via symbolic propagation
From MaRDI portal
Publication:2050096
DOI10.1007/s00165-021-00548-1OpenAlexW3167940350MaRDI QIDQ2050096
Publication date: 30 August 2021
Published in: Formal Aspects of Computing (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s00165-021-00548-1
verificationrobustnessLipschitz constantabstract interpretationdeep neural networksymbolic propagation
Related Items (2)
\textsf{CLEVEREST}: accelerating CEGAR-based neural network verification via adversarial attacks ⋮ PRODeep
Uses Software
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
- Verification of deep convolutional neural networks using ImageStars
- An abstraction-based framework for neural network verification
- A game-based approximate verification of deep neural networks with provable guarantees
- Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
This page was built for publication: Enhancing robustness verification for deep neural networks via symbolic propagation
