Verifying Probabilistic Specifications with Functional Lagrangians

02/18/2021
by   Leonard Berrada, et al.
0

We propose a general framework for verifying input-output specifications of neural networks using functional Lagrange multipliers that generalizes standard Lagrangian duality. We derive theoretical properties of the framework, which can handle arbitrary probabilistic specifications, showing that it provably leads to tight verification when a sufficiently flexible class of functional multipliers is chosen. With a judicious choice of the class of functional multipliers, the framework can accommodate desired trade-offs between tightness and complexity. We demonstrate empirically that the framework can handle a diverse set of networks, including Bayesian neural networks with Gaussian posterior approximations, MC-dropout networks, and verify specifications on adversarial robustness and out-of-distribution(OOD) detection. Our framework improves upon prior work in some settings and also generalizes to new stochastic networks and probabilistic specifications, like distributionally robust OOD detection.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/25/2019

Verification of Non-Linear Specifications for Neural Networks

Prior work on neural network verification has focused on specifications ...
research
02/23/2022

Learning Neural Networks under Input-Output Specifications

In this paper, we examine an important problem of learning neural networ...
research
06/21/2023

Verifying Global Neural Network Specifications using Hyperproperties

Current approaches to neural network verification focus on specification...
research
12/15/2020

Scalable Verification of Quantized Neural Networks (Technical Report)

Formal verification of neural networks is an active topic of research, a...
research
02/09/2022

Stability Analysis of Recurrent Neural Networks by IQC with Copositive Mutipliers

This paper is concerned with the stability analysis of the recurrent neu...
research
06/30/2020

Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications

Recent work has shown that it is possible to learn neural networks with ...
research
03/19/2018

Ready, Set, Verify! Applying hs-to-coq to real-world Haskell code

Good tools can bring mechanical verification to programs written in main...

Please sign up or login with your details

Forgot password? Click here to reset