A Study on Mixup-Inspired Augmentation Methods for Software Vulnerability Detection
This work addresses dataset scarcity and imbalance for software vulnerability detection, but it is incremental as it adapts existing methods from a different domain without surpassing simple baselines.
The paper tackled the problem of limited and imbalanced datasets for software vulnerability detection by exploring representation-level augmentation techniques, resulting in an F1-score increase of up to 9.67% but not surpassing random oversampling, which achieved a 10.82% gain.
Various deep learning (DL) methods have recently been utilized to detect software vulnerabilities. Real-world software vulnerability datasets are rare and hard to acquire, as there is no simple metric for classifying vulnerability. Such datasets are heavily imbalanced, and none of the current datasets are considered huge for DL models. To tackle these problems, a recent work has tried to augment the dataset using the source code and generate realistic single-statement vulnerabilities, which is not quite practical and requires manual checking of the generated vulnerabilities. In this paper, we aim to explore the augmentation of vulnerabilities at the representation level to help current models learn better, which has never been done before to the best of our knowledge. We implement and evaluate five augmentation techniques that augment the embedding of the data and have recently been used for code search, which is a completely different software engineering task. We also introduced a conditioned version of those augmentation methods, which ensures the augmentation does not change the vulnerable section of the vector representation. We show that such augmentation methods can be helpful and increase the F1-score by up to 9.67%, yet they cannot beat Random Oversampling when balancing datasets, which increases the F1-score by 10.82%.