An SMT-Based Approach for Verifying Binarized Neural Networks
An SMT-Based Approach for Verifying Binarized Neural Networks
复制标题
一种基于SMT的方法，用于验证二进制神经网络
DOI：
10.1007/978-3-030-72013-1_11
复制
发表时间：
2021-02-26
期刊：
影响因子：
--
通讯作者：
Katz G
中科院分区：
文献类型：
--
作者：
Amir G;Wu H;Barrett C;Katz G
深度学习是一种有效的方法来创建现代软件系统，不幸的是，神经网络经常冲浪。通过正式证明网络是正确的。网络已经对某些权重进行了二进制，以使神经网络更加有效，并且可以更快地评估我们的技术。神经网络验证在计算上非常困难，因此我们在这里提出了各种优化，并将其集成为SMT程序作为扣除步骤，以及一种方法并行验证查询。
Deep learning has emerged as an effective approach for creating modern software systems, with neural networks often surpassing hand-crafted systems. Unfortunately, neural networks are known to suffer from various safety and security issues. Formal verification is a promising avenue for tackling this difficulty, by formally certifying that networks are correct. We propose an SMT-based technique for verifying binarized neural networks — a popular kind of neural network, where some weights have been binarized in order to render the neural network more memory and energy efficient, and quicker to evaluate. One novelty of our technique is that it allows the verification of neural networks that include both binarized and non-binarized components. Neural network verification is computationally very difficult, and so we propose here various optimizations, integrated into our SMT procedure as deduction steps, as well as an approach for parallelizing verification queries. We implement our technique as an extension to the Marabou framework, and use it to evaluate the approach on popular binarized neural network architectures.
DOI：
10.1007/978-3-030-53288-8_3
发表时间：
2020-06-13
期刊：
Computer Aided Verification
影响因子：
--
作者：
Elboher YY;Gottschlich J;Katz G
通讯作者：
Katz G
DOI：
10.1007/978-3-030-53288-8_2
发表时间：
2020-06-13
期刊：
Computer Aided Verification
影响因子：
--
作者：
Tran HD;Bak S;Xiang W;Johnson TT
通讯作者：
Johnson TT
DOI：
10.1007/978-3-030-45237-7_5
发表时间：
2020-03-13
期刊：
Tools and Algorithms for the Construction and Analysis of Systems
影响因子：
--
作者：
Giacobbe M;Henzinger TA;Lechner M
通讯作者：
Lechner M