
This paper investigates methods for collecting network flow information from recorded network traffic in order to create a dataset for training anomaly-based malicious traffic detection models. The results created by nProbe and a Python script using the Scapy library were compared. The results showed that nProbe, a tool designed for collecting network flows, generates network flows from recorded traffic more accurately, faster, and more efficiently. The conclusion is that it is generally more worthwhile to use nProbe for network traffic analysis.
Ovaj rad istražuje metode skupljanja informacija o mrežnim tokovima iz snimljenog mrežnog prometa u svrhu stvaranja skupa podataka za učenje modela detekcija zloćud- nog prometa na temelju anomalija. Uspoređivali su se rezultati alata nProbe i Python skripta koja koristi biblioteku Scapy. Rezultati su pokazali da nProbe, alat kojemu je namjena prikupljanje mrežnih tokova, točnije, brže i efikasnije generira mrežne tokove iz snimljenog prometa. Zaključak je da je u svrhu analize mrežnog prometa generalno isplativije koristiti alat nProbe.
Network traffic analysis, TECHNICAL SCIENCES. Computing., TEHNIČKE ZNANOSTI. Računarstvo., NetFlow, Network flows, Sigurnost mreža, Network security, Analiza mrežnog prometa, Mrežni tokovi, Python, Scapy
Network traffic analysis, TECHNICAL SCIENCES. Computing., TEHNIČKE ZNANOSTI. Računarstvo., NetFlow, Network flows, Sigurnost mreža, Network security, Analiza mrežnog prometa, Mrežni tokovi, Python, Scapy
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
