create signature rule with the results of machine learning methods

blend ajazi via Snort-sigs <[email protected]>
Newsgroups gmane.comp.security.ids.snort.sigs
Message-ID <DU0P195MB147384162F9C7E53D26BA3C1D7659@DU0P195MB1473.EURP195.PROD.OUTLOOK.COM>
Hello Snort Community,

I am a student who just started working with snort.

Below is a result of a decision tree (DT):
(The target of the DT is to determine whether a dataset is a cyber-attack or not.)

1       if (N_IN_Conn_P_DstIP > 99.5) and (N_IN_Conn_P_SrcIP <= 99.5) and (max > 0.213) and (srate <= 4.86) and (srate > 0.024) and (max > 2.163) and (srate <= 1.112) and (max <= 4.109) and (max <= 4.095) and (srate <= 0.805) then class: DDoS (proba: 100.0%) | based on 102,730 samples


Feature Selection       Description
N_IN_Conn_P_SrcIP       Number of inbound connections per source IP.
N_IN_Conn_P_DstIP       Number of inbound connections per destination IP.
Srate   Source-to-destination packets per second
Max     Maximum duration of aggregated records


How can I convert this DT-output in a signature rule in snort?

drop tcp any any -> any any (
msg: "DDoS attack"
if (N_IN_Conn_P_DstIP > 99.5)
and (N_IN_Conn_P_SrcIP <= 99.5)
and (max > 0.213) and (srate <= 4.86)
and (srate > 0.024) and (max > 2.163)
and (srate <= 1.112) and (max <= 4.109)
and (max <= 4.095) and (srate <= 0.805)
sid:100001
)

I would appreciate any direction of approach with this task.

Thank you for the support!


Mit freundlichen Grüßen
Best regards

Blend Ajazi

_______________________________________________
Snort-sigs mailing list
[email protected]
https://lists.snort.org/mailman/listinfo/snort-sigs

Please visit http://blog.snort.org for the latest news about Snort!

Please follow these rules: https://snort.org/faq/what-is-the-mailing-list-etiquette

Visit the Snort.org to subscribe to the official Snort ruleset, make sure to stay up to date to catch the most <a href=" https://snort.org/downloads/#rule-downloads">emerging threats</a>!
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.