Cyber Crime and usage of Confusion Matrix, and it’s two types of errors.
TASK-5 . Summer Training 2021 .
Task Description 📄
📌 Create a blog/article/video about cyber crime cases where they talk about confusion matrix or its two types of error.
With the passage of time, Internet has become a part of our everyday life, which also gave a rise in cases of Cybercrime.
Cybercrime refers to any form of a crime involving a computer or other electronic device. Recent cyber crimes encompass illicit activity such as using a Trojan to seize control of an online banking account. Cybercrime cases can also involve demanding an extortion payment after infecting a victimized organization’s computers with ransomware or impairing its operations through a distributed denial-of-service (DDoS) attack.
As the cases increase daily, evaluating the attacks and provide protective measures for future attacks will be difficult because the amount of data which needs to be evaluated will be huge, and it will be time-consuming.
With the use of machine learning algorithms it can help automate the task of evaluating the cause of the attack and also help in determining the attack in real time. Here we try to understand the use of Confusion Matrix in the field of Cybersecurity.
Understanding Confusion Matrix
A confusion matrix is a performance measurement technique for machine learning classification problems. It’s a simple table which helps us to know the performance of the classification model on test data as the true values are known. It is also known as error matrix as it shows errors in the performance model.
The matrix is divided into two dimensions, predicted values and Actual Values. The table has four different combinations of predicted values and actual values:
- True Negative - When the predicted value is No and the real value also says No, then it is known as True Negative.
- False Positive - When the predicted value is Yes and the actual value is No, it is known as False Positive(Type-I Error).
- False Negative - When the predicted value is No and the actual value is also No, then it is known as False Negative(Type-II Error).
- True Positive - When the predicted value is Yes and the actual value is also Yes, then it is known as True Positive.
This is useful to measure Accuracy, Precision and Recall.
There are two types of errors in this confusion matrix.
Type-I(False Positive) & Type-II(False Negative).
How the errors help?
Type-I Error:
Also known as False Positive. This is when no attack is predicted, but an attack is taking place in real time, and no warning is given out and the no counter measures are taken for it, which results in damage to the system. This can be dangerous and measures should be taken.
Type-II Error:
Also known as False Negative. This is when an attack is predicted, but no attack is taking place in real time, this can cause a False Alarm at times.
This can help in making the system better.
