\textsf{BDD4BNN}: a BDD-based quantitative analysis framework for binarized neural networks
From MaRDI portal
Publication:832164
DOI10.1007/978-3-030-81685-8_8zbMath1493.68226arXiv2103.07224OpenAlexW3183549096MaRDI QIDQ832164
Guangke Chen, Zhe Zhao, Fu Song, Yedi Zhang, Taolue Chen
Publication date: 25 March 2022
Full work available at URL: https://arxiv.org/abs/2103.07224
Artificial neural networks and deep learning (68T07) Specification and verification (program logics, model checking, etc.) (68Q60)
Related Items
\textsf{CLEVEREST}: accelerating CEGAR-based neural network verification via adversarial attacks, Quantitative Verification for Neural Networks using ProbStars
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Constrained image generation using binarized neural networks with decision procedures
- A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability
- Improving neural network verification through spurious region guided refinement
- An SMT theory of fixed-point arithmetic
- Safety verification of deep neural networks
- Reluplex: an efficient SMT solver for verifying deep neural networks
- Assessing heuristic machine learning explanations with model counting
- Verifying binarized neural networks by Angluin-style learning
- Verification of deep convolutional neural networks using ImageStars
- An abstraction-based framework for neural network verification
- An SMT-based approach for verifying binarized neural networks
- An efficient query learning algorithm for ordered binary decision diagrams
- Graph-Based Algorithms for Boolean Function Manipulation
- Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
- How Many Bits Does it Take to Quantize Your Neural Network?