Zonotope Domains for Lagrangian Neural Network Verification

10/14/2022
by   Matt Jordan, et al.
0

Neural network verification aims to provide provable bounds for the output of a neural network for a given input range. Notable prior works in this domain have either generated bounds using abstract domains, which preserve some dependency between intermediate neurons in the network; or framed verification as an optimization problem and solved a relaxation using Lagrangian methods. A key drawback of the latter technique is that each neuron is treated independently, thereby ignoring important neuron interactions. We provide an approach that merges these two threads and uses zonotopes within a Lagrangian decomposition. Crucially, we can decompose the problem of verifying a deep neural network into the verification of many 2-layer neural networks. While each of these problems is provably hard, we provide efficient relaxation methods that are amenable to efficient dual ascent procedures. Our technique yields bounds that improve upon both linear programming and Lagrangian-based verification techniques in both time and bound tightness.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/17/2018

A Dual Approach to Scalable Verification of Deep Networks

This paper addresses the problem of formally verifying desirable propert...
research
02/02/2023

Provably Bounding Neural Network Preimages

Most work on the formal verification of neural networks has focused on b...
research
04/14/2021

Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition

We improve the scalability of Branch and Bound (BaB) algorithms for form...
research
04/17/2020

Parallelization Techniques for Verifying Neural Networks

Inspired by recent successes with parallel optimization techniques for s...
research
02/24/2020

Lagrangian Decomposition for Neural Network Verification

A fundamental component of neural network verification is the computatio...
research
03/06/2022

A Unified View of SDP-based Neural Network Verification through Completely Positive Programming

Verifying that input-output relationships of a neural network conform to...
research
01/14/2021

Scaling the Convex Barrier with Active Sets

Tight and efficient neural network bounding is of critical importance fo...

Please sign up or login with your details

Forgot password? Click here to reset