Fast Neural Network Verification via Shadow Prices

02/19/2019
by   Vicenc Rubies Royo, et al.
0

To use neural networks in safety-critical settings it is paramount to provide assurances on their runtime operation. Recent work on ReLU networks has sought to verify whether inputs belonging to a bounded box can ever yield some undesirable output. Input-splitting procedures, a particular type of verification mechanism, do so by recursively partitioning the input set into smaller sets. The efficiency of these methods is largely determined by the number of splits the box must undergo before the property can be verified. In this work, we propose a new technique based on shadow prices that fully exploits the information of the problem yielding a more efficient generation of splits than the state-of-the-art. Results on the Airborne Collision Avoidance System (ACAS) benchmark verification tasks show a considerable reduction in the partitions generated which substantially reduces computation times. These results open the door to improved verification methods for a wide variety of machine learning applications including vision and control.

READ FULL TEXT
research
08/07/2023

Expediting Neural Network Verification via Network Reduction

A wide range of verification methods have been proposed to verify the sa...
research
07/16/2021

Constrained Feedforward Neural Network Training via Reachability Analysis

Neural networks have recently become popular for a wide variety of uses,...
research
12/15/2022

Optimized Symbolic Interval Propagation for Neural Network Verification

Neural networks are increasingly applied in safety critical domains, the...
research
12/03/2020

Towards Repairing Neural Networks Correctly

Neural networks are increasingly applied to support decision making in s...
research
07/21/2022

CheckINN: Wide Range Neural Network Verification in Imandra (Extended)

Neural networks are increasingly relied upon as components of complex sa...
research
06/18/2023

GPU-Accelerated Verification of Machine Learning Models for Power Systems

Computational tools for rigorously verifying the performance of large-sc...
research
11/17/2018

Statistical Verification of Neural Networks

We present a new approach to neural network verification based on estima...

Please sign up or login with your details

Forgot password? Click here to reset