Vision of Active Learning Framework Approach to Network Traffic Analysis Research

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F22%3A00358729" target="_blank" >RIV/68407700:21240/22:00358729 - isvavai.cz</a>

Výsledek na webu

<a href="https://pesw.fit.cvut.cz/2022/PESW_2022.pdf" target="_blank" >https://pesw.fit.cvut.cz/2022/PESW_2022.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Vision of Active Learning Framework Approach to Network Traffic Analysis Research

Popis výsledku v původním jazyce

Current research in the network security domain intensively uses machine learning (ML) and artificial intelligence to automate processes and reveal hidden patterns in data. These technologies, however, require lots of training datasets with ideally high quality. Additionally, network infrastructures continuously evolve and thus network traffic dynamically changes in time as well. There is an urgent need to adapt machine learning models, update datasets with the latest samples of annotated network traffic and retrain the models regularly to sustain feasible performance. Active Learning Framework (ALF) directly targets these demands and aims to provide a modular platform for scientific experiments and deployment in practice as well as to support research activities regarding quality of datasets. This paper particularly describes ALF software and proposes its possible use cases in research and practice domains.

Název v anglickém jazyce

Vision of Active Learning Framework Approach to Network Traffic Analysis Research

Popis výsledku anglicky

Current research in the network security domain intensively uses machine learning (ML) and artificial intelligence to automate processes and reveal hidden patterns in data. These technologies, however, require lots of training datasets with ideally high quality. Additionally, network infrastructures continuously evolve and thus network traffic dynamically changes in time as well. There is an urgent need to adapt machine learning models, update datasets with the latest samples of annotated network traffic and retrain the models regularly to sustain feasible performance. Active Learning Framework (ALF) directly targets these demands and aims to provide a modular platform for scientific experiments and deployment in practice as well as to support research activities regarding quality of datasets. This paper particularly describes ALF software and proposes its possible use cases in research and practice domains.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/VJ02010024" target="_blank" >VJ02010024: Analýza šifrovaného provozu pomocí síťových toků</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů