Reader small image

You're reading from  Hands-On Artificial Intelligence for Cybersecurity

Product typeBook
Published inAug 2019
Reading LevelBeginner
PublisherPackt
ISBN-139781789804027
Edition1st Edition
Languages
Right arrow
Author (1)
Alessandro Parisi
Alessandro Parisi
author image
Alessandro Parisi

Alessandro Parisi has been an IT professional for over 20 years, acquiring significant experience as a Security Data Scientist, and as an Artificial Intelligence Cybersecurity and Blockchain specialist. He has experience of operating within organizational and decisional contexts characterized by high complexity. Over the years, he has helped companies to adopt Artificial Intelligence and Blockchain DLT technologies as strategic tools in protecting sensitive corporate assets. He holds a Master Degree in Economics and Statistics.
Read more about Alessandro Parisi

Right arrow

Evaluating a detector's performance with ROC

We have previously encountered the ROC curve and AUC measure (Chapter 5, Network Anomaly Detection with AI, and Chapter 7, Fraud Prevention with Cloud AI Solutions) to evaluate and compare the performance of different classifiers.

Now let's explore the topic in a more systematic way, introducing the confusion matrix associated with all the possible results returned by a fraud-detection classifier, comparing the predicted values with the real values:

We can then calculate the following values (listed with their interpretation) based on the previous confusion matrix:

  • Sensitivity = Recall = Hit rate = TP/(TP + FP): This value measures the rate of correctly labeled fraudsters and represents the true positive rate (TPR)
  • False Positive Rate (FPR) = FP/(FP + TN): FPR is also calculated as 1 – Specificity
  • Classification accuracy...
lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Hands-On Artificial Intelligence for Cybersecurity
Published in: Aug 2019Publisher: PacktISBN-13: 9781789804027

Author (1)

author image
Alessandro Parisi

Alessandro Parisi has been an IT professional for over 20 years, acquiring significant experience as a Security Data Scientist, and as an Artificial Intelligence Cybersecurity and Blockchain specialist. He has experience of operating within organizational and decisional contexts characterized by high complexity. Over the years, he has helped companies to adopt Artificial Intelligence and Blockchain DLT technologies as strategic tools in protecting sensitive corporate assets. He holds a Master Degree in Economics and Statistics.
Read more about Alessandro Parisi