English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The popularity of Deep Learning (DL), coupled with network traffic visibilityreduction due to the increased adoption of HTTPS, QUIC and DNS-SEC, re-ignitedinterest towards Traffic Classification (TC). However, to tame the dependencyfrom task-specific large labeled datasets we need to find better ways to learnrepresentations that are valid across tasks. In this work we investigate thisproblem comparing transfer learning, meta-learning and contrastive learningagainst reference Machine Learning (ML) tree-based and monolithic DL models (16methods total). Using two publicly available datasets, namely MIRAGE19 (40classes) and AppClassNet (500 classes), we show that (i) using large datasetswe can obtain more general representations, (ii) contrastive learning is thebest methodology and (iii) meta-learning the worst one, and (iv) while MLtree-based cannot handle large tasks but fits well small tasks, by means ofreusing learned representations, DL methods are reaching tree-based modelsperformance also for small tasks.

Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification