Semisupervised Learning with Data Augmentation for Raw Network Traffic Detection

Deep learning (DL) has revolutionized machine learning tasks in various domains, but conventional DL methods often demand substantial amounts of labeled data. Semi-supervised learning (SSL) provides an effective solution by incorporating unlabeled data, offering s ignificant advantages in terms of cost and data accessibility. While DL has shown promise with its integration as a component of modern network intrusion detection systems (NIDS), the majority of research in this field f ocuses o n f ully s upervised l earning. However, more recent SSL algorithms leveraging data augmentations do not perform optimally "out of the box" due to the absence of suitable augmentation schemes for packet-level network traffic da ta. Th rough th e in troduction of a novel data augmentation scheme tailored to packet-level network traffic datasets, this paper presents a comprehensive analysis of multiple SSL algorithms for multi-class network traffic detection in a few-shot learning sc enario. We find t hat e ven r elatively s imple a pproaches l ike vanilla p seudo-labeling c an a chieve a n F1-Score t hat i s within 5% of fully supervised learning methods while utilizing less than 2% of the labeled data.