Prompting Creative Requirements via Traceable and Adversarial Examples in Deep Learning

• Published in: 2023 IEEE 31st International Requirements Engineering Conference (RE) pp. 134 - 145
• Main Authors: Gudaparthi, Hemanth, Niu, Nan, Wang, Boyang, Bhowmik, Tanmay, Liu, Hui, Zhang, Jianzhang, Savolainen, Juha, Horton, Glen, Crowe, Sean, Scherz, Thomas, Haitz, Lisa
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-09-2023
• Subjects: adversarial examples; automated requirements generation; Behavioral sciences; Computer architecture; creative requirements; Deep learning; Instruments; Perturbation methods; Requirements engineering; Software
• ISSN: 2332-6441
• DOI: 10.1109/RE57278.2023.00022

Creativity focuses on the generation of novel and useful ideas. In this paper, we propose an approach to automatically generating creative requirements candidates via the adversarial examples resulted from applying small changes (perturbations) to the original requirements descriptions. We present an architecture where the perturbator and the classifier positively influence each other. Meanwhile, we ensure that each adversarial example is uniquely traceable to an existing feature of the software, instrumenting explainability. Our experimental evaluation of six datasets shows that around 20% adversarial shift rate is achievable. In addition, a human subject study demonstrates our results are more clear, novel, and useful than the requirements candidates outputted from a state-of-the-art machine learning method. To connect the creative requirements closer with software development, we collaborate with a software development team and show how our results can support behavior-driven development for a web app built by the team.