An SMT-Based Approach for Verifying Binarized Neural Networks

11/05/2020
by   Guy Amir, et al.
0

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 networks, 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/03/2017

Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

Deep neural networks have emerged as a widely used and effective means f...
research
05/17/2021

DISCO Verification: Division of Input Space into COnvex polytopes for neural network verification

The impressive results of modern neural networks partly come from their ...
research
01/27/2023

OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks

Occlusion is a prevalent and easily realizable semantic perturbation to ...
research
07/13/2020

Neural Network Verification through Replication

A system identification based approach to neural network model replicati...
research
09/05/2022

Exploring the Verifiability of Code Generated by GitHub Copilot

GitHub's Copilot generates code quickly. We investigate whether it gener...
research
10/23/2022

Tighter Abstract Queries in Neural Network Verification

Neural networks have become critical components of reactive systems in v...
research
05/03/2017

Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks

We present an approach for the verification of feed-forward neural netwo...

Please sign up or login with your details

Forgot password? Click here to reset