SINVAD: Search-based Image Space Navigation for DNN Image Classifier Test Input Generation
This addresses the problem of testing DNNs in safety-critical systems by enabling more meaningful exploration of structured image spaces, though it is incremental as it builds on existing VAE and search-based techniques.
The paper tackles the challenge of automated test input generation for deep neural networks (DNNs) by proposing a method that searches over a plausible input space constructed with Variational Autoencoders (VAEs), rather than the entire image space, to efficiently produce realistic test inputs that reveal DNN robustness issues.
The testing of Deep Neural Networks (DNNs) has become increasingly important as DNNs are widely adopted by safety critical systems. While many test adequacy criteria have been suggested, automated test input generation for many types of DNNs remains a challenge because the raw input space is too large to randomly sample or to navigate and search for plausible inputs. Consequently, current testing techniques for DNNs depend on small local perturbations to existing inputs, based on the metamorphic testing principle. We propose new ways to search not over the entire image space, but rather over a plausible input space that resembles the true training distribution. This space is constructed using Variational Autoencoders (VAEs), and navigated through their latent vector space. We show that this space helps efficiently produce test inputs that can reveal information about the robustness of DNNs when dealing with realistic tests, opening the field to meaningful exploration through the space of highly structured images.