Data Augmentation in Learning-Based Binary Code Analysis
Understanding and analyzing binary code is fundamental to many security-critical tasks, such as reverse engineering and vulnerability discovery. As machine learning has become integral to these tasks, techniques from other domains have been transferred to binary code analysis. In particular, inspired by computer vision, data augmentation has recently been proposed to improve performance in code analysis tasks. However, prior work considers only a limited set of transformations and downstream tasks, making it difficult to draw broader conclusions about when and how augmentation is effective. In this work, we thus take a step back and systematically study the role of data augmentation in binary code analysis. To this end, we introduce a unified framework that encompasses both semantic-preserving and semantic-altering code transformations for augmentation. We evaluate the impact of augmentation across multiple tasks, including function similarity, parameter analysis, and vulnerability discovery. Our findings reveal a key difference from computer vision: in binary code analysis, augmentation is not a silver bullet. While code transformations can improve performance when training data is scarce, the gains diminish as more data becomes available. We conclude that augmentation is only beneficial under specific conditions and t
