PREDICTION OF CYBER-ATTACKS USING DATA SCIENCE TECHNIQUE

COMPUTER SCIENCE AND ENGINEERING

A cyber-attack is an assault launched by cybercriminals using one or further computers against a single or multiple computers or networks for destroying the integrity of the data or stealing the information. The cyber-attack can peril disable computers, use a traduced computer as a position point for some attacks or steals public data. The Hacker use different styles to start a cyber-attack, for illustration phishing, Dos, R2L, probe, malware, U2R among other styles. Though a plethora of extant approaches, models and algorithms have handed the base for cyber-attack prognostications, there's the need to consider new models and algorithms, which are grounded on data representations other than task-specific ways. Still, its non-linear information processing architecture can be shaped towards learning the different data representations of network traffic to classify type of network attack. Networking sectors have to predict the type of Network attack from given dataset using machine learning ways. The analysis of dataset by supervised machine learning techniques( SMLT) to capture several information’s like, variable identification, variant analysis, bi-variant and multi-variant analysis, missing value treatments etc. A relative study between machine literacy algorithms had been carried out in order to determine which algorithm is the most accurate in predicting the type cyber Attacks. We classify four types of attacks are DOS Attack, Remote to user (R2L), User to Root (U2R) Attack, probe attack. The results show that the effectiveness of the proposed machine literacy algorithm fashion can be compared with accuracy with entropy calculation, performance, Recall, F1 Score, perceptivity, Particularity and Entropy.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.