An SMT-Based Approach for Verifying Binarized Neural Networks

An SMT-Based Approach for Verifying Binarized Neural Networks” by Guy Amir, Haoze Wu, Clark Barrett, and Guy Katz. In Proceedings of the 27^th International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS '21), (Jan Friso Groote and Kim Guldstrand Larsen, eds.), Mar. 2021, pp. 203-222.

Abstract

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.

BibTeX entry:

@inproceedings{AWB+21,
   author = {Guy Amir and Haoze Wu and Clark Barrett and Guy Katz},
   editor = {Jan Friso Groote and Kim Guldstrand Larsen},
   title = {An {SMT}-Based Approach for Verifying Binarized Neural Networks},
   booktitle = {Proceedings of the {\it 27^{th}} International Conference
	on Tools and Algorithms for the Construction and Analysis of
	Systems (TACAS '21)},
   series = {Lecture Notes in Computer Science},
   volume = {12652},
   pages = {203--222},
   publisher = {Springer},
   month = mar,
   year = {2021},
   doi = {10.1007/978-3-030-72013-1_11},
   url = {http://theory.stanford.edu/~barrett/pubs/AWB+21.pdf}
}

(This webpage was created with bibtex2web.)