Software Vulnerability Prediction in Low-Resource Languages: An Empirical Study of CodeBERT and ChatGPT

arXiv:2404.17110v1 Announce Type: cross
Abstract: Background: Software Vulnerability (SV) prediction in emerging languages is increasingly important to ensure software security in modern systems. However, these languages usually have limited SV data for developing high-performing prediction models. Aims: We conduct an empirical study to evaluate the impact of SV data scarcity in emerging languages on the state-of-the-art SV prediction model and investigate potential solutions to enhance the performance. Method: We train and test the state-of-the-art model based on CodeBERT with and …

arxiv chatgpt cs.cr cs.lg cs.se data emerging high impact important languages low performing prediction resource security software software security software vulnerability study systems vulnerability