Dongxia Wang

Papers

Total Citations

H-Index

About

Dongxia Wang is a leading researcher in the quality assurance of deep learning (DL) systems, with a primary focus on software engineering for AI. Her key research areas include deep learning testing, adversarial robustness, and automated bug detection in neural networks. Wang’s most notable contribution is the development of **RobOT (Robustness-Oriented Testing)**, a pioneering framework that systematically generates adversarial examples to uncover vulnerabilities in DL models. This work, published in 2021, has garnered over 63 citations, reflecting its significant impact on the field. By combining fuzzing and guided search techniques, RobOT enables more effective and scalable testing of DL systems, helping to bridge the gap between traditional software testing and modern AI reliability. Wang’s research is instrumental in advancing the safety and trustworthiness of AI applications, particularly in high-stakes domains like autonomous driving and healthcare. Her work has been widely recognized by the software engineering and AI communities, positioning her as a key figure in the emerging discipline of DL robustness testing. For students and researchers, Wang’s contributions offer a practical roadmap for building more resilient and dependable deep learning systems.