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

03/06/2022
by   Robin Brown, et al.
0

Verifying that input-output relationships of a neural network conform to prescribed operational specifications is a key enabler towards deploying these networks in safety-critical applications. Semidefinite programming (SDP)-based approaches to Rectified Linear Unit (ReLU) network verification transcribe this problem into an optimization problem, where the accuracy of any such formulation reflects the level of fidelity in how the neural network computation is represented, as well as the relaxations of intractable constraints. While the literature contains much progress on improving the tightness of SDP formulations while maintaining tractability, comparatively little work has been devoted to the other extreme, i.e., how to most accurately capture the original verification problem before SDP relaxation. In this work, we develop an exact, convex formulation of verification as a completely positive program (CPP), and provide analysis showing that our formulation is minimal – the removal of any constraint fundamentally misrepresents the neural network computation. We leverage our formulation to provide a unifying view of existing approaches, and give insight into the source of large relaxation gaps observed in some cases.

READ FULL TEXT
research
06/24/2020

The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification

We improve the effectiveness of propagation- and linear-optimization-bas...
research
06/07/2022

Parametric Chordal Sparsity for SDP-based Neural Network Verification

Many future technologies rely on neural networks, but verifying the corr...
research
10/14/2022

Zonotope Domains for Lagrangian Neural Network Verification

Neural network verification aims to provide provable bounds for the outp...
research
11/27/2022

Neural Network Verification as Piecewise Linear Optimization: Formulations for the Composition of Staircase Functions

We present a technique for neural network verification using mixed-integ...
research
10/16/2020

Strengthened SDP Verification of Neural Network Robustness via Non-Convex Cuts

There have been major advances on the design of neural networks, but sti...
research
05/05/2023

On Preimage Approximation for Neural Networks

Neural network verification mainly focuses on local robustness propertie...
research
12/03/2022

Probabilistic Verification of ReLU Neural Networks via Characteristic Functions

Verifying the input-output relationships of a neural network so as to ac...

Please sign up or login with your details

Forgot password? Click here to reset