| Autor: |
Balan, Shilpa, Howell, Pamella |
| Předmět: |
|
| Zdroj: |
ACET Journal of Computer Education & Research; 2019, Vol. 13 Issue 1, p1-10, 10p |
| Abstrakt: |
The Internet is a necessary part of our daily lives. Although the Internet has many benefits, it can compromise the security of the systems connecting to it in numerous ways. Resultantly, attacks on networks have increased in number and severity over the past few years; hence, Intrusion Detection Systems (IDSs) are a significant part of an organizations' infrastructure. Intrusion detection systems help reduce security risks by improving the network ability to resist external attacks. The objective of this paper is to examine the features impacting Brute Force SSH and FTP attacks using the Random Forest machine learning technique. We utilize a data set that includes updated network attacks and simulates real-world traffic flow. Using realistic traffic features, our prediction model achieved high accuracy when identifying Brute Force SSH and FTP attacks. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Supplemental Index |
| Externí odkaz: |
|
