Work In Progress: Safety and Robustness Verification of Autoencoder-Based Regression Models using the NNV Tool

TL;DR

This paper explores the verification of autoencoder-based regression neural networks for safety and robustness, extending existing methods to address the unique challenges of regression models and implementing these in the NNV tool.

Contribution

It introduces new robustness metrics and adapts the Imagestar approach for autoencoder-based regression models, pioneering reachability analysis for such networks.

Findings

Extended NNV with robustness metrics for regression autoencoders

Modified Imagestar approach for regression input types

First known reachability analysis of autoencoder-based NNs

Abstract

This work in progress paper introduces robustness verification for autoencoder-based regression neural network (NN) models, following state-of-the-art approaches for robustness verification of image classification NNs. Despite the ongoing progress in developing verification methods for safety and robustness in various deep neural networks (DNNs), robustness checking of autoencoder models has not yet been considered. We explore this open space of research and check ways to bridge the gap between existing DNN verification methods by extending existing robustness analysis methods for such autoencoder networks. While classification models using autoencoders work more or less similar to image classification NNs, the functionality of regression models is distinctly different. We introduce two definitions of robustness evaluation metrics for autoencoder-based regression models, specifically the percentage robustness and un-robustness grade. We also modified the existing Imagestar approach, adjusting the variables to take care of the specific input types for regression networks. The approach is implemented as an extension of NNV, then applied and evaluated on a dataset, with a case study experiment shown using the same dataset. As per the authors' understanding, this work in progress paper is the first to show possible reachability analysis of autoencoder-based NNs.