A Dual Approach to Scalable Verification of Deep Networks

03/17/2018
by   Krishnamurthy Dvijotham, et al.
0

This paper addresses the problem of formally verifying desirable properties of neural networks, i.e., obtaining provable guarantees that the outputs of the neural network will always behave in a certain way for a given class of inputs. Most previous work on this topic was limited in its applicability by the size of the network, network architecture and the complexity of properties to be verified. In contrast, our framework applies to much more general class of activation functions and specifications on neural network inputs and outputs. We formulate verification as an optimization problem and solve a Lagrangian relaxation of the optimization problem to obtain an upper bound on the verification objective. Our approach is anytime, i.e. it can be stopped at any time and a valid bound on the objective can be obtained. We develop specialized verification algorithms with provable tightness guarantees under special assumptions and demonstrate the practical significance of our general verification approach on a variety of verification tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/14/2022

Zonotope Domains for Lagrangian Neural Network Verification

Neural network verification aims to provide provable bounds for the outp...
research
06/21/2023

Verifying Global Neural Network Specifications using Hyperproperties

Current approaches to neural network verification focus on specification...
research
02/02/2023

Provably Bounding Neural Network Preimages

Most work on the formal verification of neural networks has focused on b...
research
05/06/2018

Reachability Analysis of Deep Neural Networks with Provable Guarantees

Verifying correctness of deep neural networks (DNNs) is challenging. We ...
research
02/24/2020

Lagrangian Decomposition for Neural Network Verification

A fundamental component of neural network verification is the computatio...
research
05/11/2021

Mandating Code Disclosure is Unnecessary – Strict Model Verification Does Not Require Accessing Original Computer Code

Mandating public availability of computer code underlying computational ...
research
06/09/2023

Complexity of Reachability Problems in Neural Networks

In this paper we investigate formal verification problems for Neural Net...

Please sign up or login with your details

Forgot password? Click here to reset