Hands-On Artificial Intelligence for Cybersecurity

Gaussian anomaly detection example

First of all, let's import the necessary Python libraries, and then load the data from a .csv file that represents the latency and network throughput values of each data stream we detected:

import numpy as npimport pandas as pdimport matplotlib.pyplot as plt%matplotlib inlinedataset = pd.read_csv('../datasets/network-logs.csv')

Once the data is loaded into memory, we verify whether the distribution of the samples might resemble a Gaussian distribution, displaying the corresponding values in the form of a histogram:

hist_dist = dataset[['LATENCY', 'THROUGHPUT']].hist(grid=False, figsize=(10,4))

The preceding code generates the following output:

At this point, we perform the data plotting on a scatter ...