Data Augmentation for Traffic Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929219336929280 |
|---|---|
| author | Wang, Chao Finamore, Alessandro Michiardi, Pietro Gallo, Massimo Rossi, Dario |
| author_facet | Wang, Chao Finamore, Alessandro Michiardi, Pietro Gallo, Massimo Rossi, Dario |
| contents | Data Augmentation (DA) -- enriching training data by adding synthetic samples -- is a technique widely adopted in Computer Vision (CV) and Natural Language Processing (NLP) tasks to improve models performance. Yet, DA has struggled to gain traction in networking contexts, particularly in Traffic Classification (TC) tasks. In this work, we fulfill this gap by benchmarking 18 augmentation functions applied to 3 TC datasets using packet time series as input representation and considering a variety of training conditions. Our results show that (i) DA can reap benefits previously unexplored, (ii) augmentations acting on time series sequence order and masking are better suited for TC than amplitude augmentations and (iii) basic models latent space analysis can help understanding the positive/negative effects of augmentations on classification performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10754 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Data Augmentation for Traffic Classification Wang, Chao Finamore, Alessandro Michiardi, Pietro Gallo, Massimo Rossi, Dario Machine Learning Networking and Internet Architecture Data Augmentation (DA) -- enriching training data by adding synthetic samples -- is a technique widely adopted in Computer Vision (CV) and Natural Language Processing (NLP) tasks to improve models performance. Yet, DA has struggled to gain traction in networking contexts, particularly in Traffic Classification (TC) tasks. In this work, we fulfill this gap by benchmarking 18 augmentation functions applied to 3 TC datasets using packet time series as input representation and considering a variety of training conditions. Our results show that (i) DA can reap benefits previously unexplored, (ii) augmentations acting on time series sequence order and masking are better suited for TC than amplitude augmentations and (iii) basic models latent space analysis can help understanding the positive/negative effects of augmentations on classification performance. |
| title | Data Augmentation for Traffic Classification |
| topic | Machine Learning Networking and Internet Architecture |
| url | https://arxiv.org/abs/2401.10754 |