Deep Learning-Based Out-of-distribution Source Code Data Identification: How Far We Have Gone?

arXiv:2404.05964v1 Announce Type: new
Abstract: Software vulnerabilities (SVs) have become a common, serious, and crucial concern to safety-critical security systems. That leads to significant progress in the use of AI-based methods for software vulnerability detection (SVD). In practice, although AI-based methods have been achieving promising performances in SVD and other domain applications (e.g., computer vision), they are well-known to fail in detecting the ground-truth label of input data (referred to as out-of-distribution, OOD, data) lying far away from the training …

arxiv code critical cs.cr data deep learning detection distribution far identification practice progress safety safety-critical security serious software software vulnerabilities software vulnerability source code systems vulnerabilities vulnerability vulnerability detection