SINVAD: Search-based Image Space Navigation for DNN Image Classifier Test Input Generation
Paper in proceeding, 2020

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.

Test Data Generation

Search-based Software Engineering

Neural Network

Author

Sungmin Kang

Korea Advanced Institute of Science and Technology (KAIST)

Robert Feldt

Chalmers, Computer Science and Engineering (Chalmers), Software Engineering (Chalmers)

Shin Yoo

Korea Advanced Institute of Science and Technology (KAIST)

Proceedings - 2020 IEEE/ACM 42nd International Conference on Software Engineering Workshops, ICSEW 2020

521-528
9781450379632 (ISBN)

42nd IEEE/ACM International Conference on Software Engineering Workshops, ICSEW 2020
Seoul, South Korea,

Subject Categories

Geotechnical Engineering

Computer Science

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1145/3387940.3391456

More information

Latest update

1/3/2024 9