Confusion Matrics And CyberSecurity

At the end of the day, the goals are simple: safety and security.

This article disscus about the role of confusion matrics in cyber-crime, before going in deep, let us understand What exactly confusion matrics is and the Cyber-Crime ?

CyberCrime — Unauthorized, Unlawful and Undefinable.

S omeone or group of people is using the technology in a bad way to get access to people’s bank account, social media profile and e-mail account to steal, post without permission or gather information about something secret. This kind of act is call cybercrime.

Cybercrime can simply be defined as any illegal action taken with the intention to harm or not harm someone or group of people using a computer or the internet, attacks in computer and internet environments bysending viruses, malware malicious codes, worms and Trojans, phishing e-mails and social networks, maliciousinsiders,web-based attacks and so on…

This is the portal where you can report any CyberCrime https://www.cybercrime.gov.in/Accept.aspx

Confusion Matrics — Sensitivity, Spesitivity and Accuracy

The Confusion matrics is the performance mesurment technique for Machine Learning Classification Problems by determining the accuracy, precision, etc of the model by using Predicted and Actual Values.

Let’s now define the most basic terms, which are whole numbers (not rates):

  • True Positive (TP) is the number of correct predictions that an example is positive which means positive class correctly identified as positive.
  • False Negative (FN) is the number of incorrect predictions that an example is negative which means positive class incorrectly identified as negative.
  • False positive (FP) is the number of incorrect predictions that an example is positive which means negative class incorrectly identified as positive.
  • True Negative (TN) is the number of correct predictions that an example is negative which means negative class correctly identified as negative..

Role of Confusion Matrix in Cyber Crime—

1. We Can Create Phishing URL Detection With Python And ML

  • Is misspelled
  • Points to the wrong top-level domain
  • A combination of a valid and a fraudulent URL
  • Is incredibly long
  • Is just be an IP address
  • Has a low pagerank
  • Has a young domain age

You can find the criteria for evaluating phishing URLs in UC Irvine’s dataset.

2. Network traffic analysis —

In data mining techniques, many different metrics are used to investigate the data mining techniques.

The detection rate, false positive rate, accuracy and time cost metrics are employed for measuring the performance of classifier for different data set.

A number of metrics exist to express predictive accuracy. The metrics used using confusion matrix.

3. Attack and anomaly detection in IoT sensors —

From the confusion matrices it can be concluded that RF is the best technique for this work. RF classified every class correctly except DoS and Normality classes.

The confusion matrix results suggest that the KNN and LDA classifiers classify the majority of packets as plug devices, while the RF classifier successfully separates the two device types.

4. Using Parallel Support Vector Machine —

Cyberattack detection is a classification problem, in which we classify the normal pattern from the abnormal pattern (attack) of the system.

This error causes problems in the cybersecurity world where the tools used are based on machine learning or ai, it may give a False Negative error that may cause dangerous impacts.

— — — — — — — — — — — — — — — — — — — — — — — — — — — — —