Jeongju Sohn

Search Based Repair of Deep Neural Networks.

2019 · arXiv (Cornell University)

Deep Neural Networks (DNNs) are being adopted in various domains, including safety critical ones. The wide-spread adoption also calls for ways to guide the testing of their accuracy and robustness, for which various test adequacy …

CEMENT: On the Use of Evolutionary Coupling Between Tests and Code Units. A Case Study on Fault Localization

2022

Many software engineering techniques, such as fault localization, operate based on relevance relationships between tests and code. These relationships are often inferred using dynamic test execution information that approximates the link between relevant code units …

TraceJIT: Evaluating the Impact of Behavioral Code Change on Just-In-Time Defect Prediction

2024

Just-In-Time (JIT) defect prediction strives to model changes that induce future fixes so that they can be predicted or better understood to inform development practices. Prior work demonstrates that the majority of the predictive/explanatory power …