ymirsky / kitnet-py Goto Github PK

Hi,

I have a question on the m parameter, if we set m to 1 we only have auto encoder with an input dimension of 1, so how do you avoid to learn the identity ? Maybe I misunderstood something.

When the model is trained, how to save it for next prediction

When I visited the link of the full dataset, the folders presented in the current website are empty. Therefore, I want to know where can I obtain this dataset? Thank you!

I've created a csv file from active wiretap pcap and trying to use it on this code.

My input data has seven fields and look like this

Reading Sample dataset...
[[0.0 0 '192.168.2.13' '192.168.100.5' '51010' '56514' 209]
[0.000773 0 '192.168.2.13' '192.168.100.5' '51010' '56514' 1514]
[0.000905 0 '192.168.2.13' '192.168.100.5' '51010' '56514' 1514]
[0.001122 0 '192.168.2.13' '192.168.100.5' '51010' '56514' 1514]
[0.001247 0 '192.168.2.13' '192.168.100.5' '51010' '56514' 1514]]

Fields =[ 'Time', 'IP_Version', 'IP_Source', 'IP_Dest', 'Source_PORT', 'Dest_PORT', 'payload' ]

But when I run the code here in kitnet it gives me the error

TypeError: ufunc 'add' output (typecode 'O') could not be coerced to provided output parameter (typecode 'd') according to the casting rule ''same_kind''

But all data in each column has same type and time represent in float while ip version and payload are integers as used in original kitsune. Would like to know what causes this ?

hello, your work is quite remarkable, and I am really interested in it,but is it possble to reveal the ip of each item in the original pcap file,especially the network used in mirai attack?thank you very much

Hello. i want to cite this paper, but I don’t understand something:

The largest RMSE of the output layer is set as the φ(cutoff-threshold) in kitnet, then:
a) Execute: s = RMSE(~ x,h θ (~ x))
b) Verdict: if(s ≥ φβ) then Alert

i dont know How to determine β，‘In the paper uses the raw RMSE score’, Does that mean β=1?

I ran an example of this project using Ubuntu18, Python3.6.5, and got the following result.However, this result graph is not consistent with the result graph you shared.This result graph does not reflect the attack, and the data under attack appears to be drawn in the wrong place. I would appreciate if you can tell me why and how to get the right result!