TO: Professor Jason Ellis
FROM: Ali Hossain
DATE:03/20/2021
SUBJECT: Expanded Definition of Cybersecurity.
Cybersecurity and Enhancement of Cybersecurity:
This document will explain why and how to enhance cybersecurity. Computer security, cybersecurity or information technology security (IT security) is the protection of computer systems and networks from information disclosure, theft of or damage to their hardware, software, or electronic data, as well as from the disruption or misdirection of the services they provide. With associate degree increasing variety of users, devices and programs within the trendy enterprise, combined with the accumulated deluge of information — a lot of that is sensitive or confidential — the importance of cybersecurity continues to grow. The growing volume and class of cyber attackers and attack techniques compound the matter even further. With AN increasing variety of users, devices and programs within the fashionable enterprise, combined with the exaggerated deluge of knowledge — a lot of that is sensitive or confidential — the importance of cybersecurity continues to grow. The growing volume and class of cyber attackers and attack techniques compound the matter even further. Reducing model complexity, improve prediction accuracy and assess exploitability are the topic that will be explained throughout the document.
“In the last few years, advancement in Artificial Intelligent (AI) such as machine learning and deep learning techniques has been used to improve IoT IDS (Intrusion Detection System).”
Dynamic Feature Selector:
“Dynamic Feature Selector (DFS) uses statistical analysis and feature importance tests to reduce model complexity and improve prediction accuracy.”
Using normal human selection is a lot slower and have higher feature size. Whereas dynamic feature selector is the only way to go. The energetic and intelligent highlights of programming dialects are powerful develops that software engineers regularly say as amazingly valuable. However, the capacity to adjust a program at runtime can be both a boon—in terms of flexibility—, and a curse—in terms of device back. For occasion, utilization of these features hampers the plan of sort frameworks, the precision of inactive investigation tech- neq, or the presentation of optimizations by compilers. In this paper, we perform an observational consider of a expansive Smalltalk codebase—often respected as the poster- child in terms of accessibility of these features—, in arrange to evaluate how much these features are really utilized in hone, whether a few are utilized more than others, and in which sorts of ventures. In expansion, we performed a subjective investigation of a agent test of utilizations of energetic highlights in arrange to reveal the principal reasons that drive individuals to utilize energetic highlights, and whether and how these energetic highlight utilized
Necessity of Dynamic Feature Selector
The Internet of Things has a great influence over system which have attracted a lot of cybercriminal to do malicious attack and open an end node to attack continuously. To prevent huge data loss it is crucial to detect infiltration and intruders. Reducin0g model Complexity and improving prediction accuracy can do the work. Machine learning and Deep machine learning are helping the matter of detecting intruder.
“Abstract Machine learning algorithms are becoming very efficient in intrusion detection systems with their real time response and adaptive learning process.”
Statistical analysis and feature importance tests can be used to reduce model complexity and improve prediction accuracy. This is where dynamic feature selector comes to rescue. DFS showed high accuracy and reduce in feature size.
“For NSL-KDD, experiments revealed an increment in accuracy from 99.54% to 99.64% while reducing feature size of one-hot encoded features from 123 to 50. In UNSW-NB15 we observed an increase in accuracy from 90.98% to 92.46% while reducing feature size from 196 to 47.”
It is clear that the new process is much accurate and less feature are required for processing.
Model Complexity, Prediction Accuracy and Exploitability:
In machine learning, model complexity often refers to the number of features or terms included in a given predictive model, as well as whether the chosen model is linear, nonlinear, and so on. It can also refer to the algorithmic learning complexity or computational complexity. Accuracy is defined as the percentage of correct predictions for the test data. It can be calculated easily by dividing the number of correct predictions by the number of total predictions. An exploit is any attack that takes advantage of vulnerabilities in applications, networks, operating systems, or hardware. Exploits usually take the form of software or code that aims to take control of computers or steal network data.
Reference:
Alazab.A.,& Khraisat.A.(2021), Cybersecurity, A critical review of intrusion detection systems in the internet of things: techniques, deployment strategy, validation strategy, attacks, public datasets and challenges, 4, Article number: 18(2021).
Ahsan.M., Gomes.R., Chowdhury.M.M., & Nygard.K.E.(2021), Enhancing Machine Learning Prediction in Cybersecurity Using Dynamic Feature Selector, J. Cybersecur. Priv. 2021, 1(1), 199-218.
