Open AccessThe Review of Artificial Intelligence in Cyber Security
Author(s) -
G. A. Sivasankar
Publication year - 2022
Publication title -
international journal for research in applied science and engineering technology
Language(s) - English
Resource type - Journals
ISSN - 2321-9653
DOI - 10.22214/ijraset.2022.40072
Subject(s) - computer science , artificial intelligence , malware , machine learning , computer security , botnet , decision tree , identification (biology) , authentication (law) , cloud computing , world wide web , the internet , operating system , botany , biology
In today's world, cyber security and artificial intelligence (AI) are two growing technologies. AI is built on the foundation of machine learning (ML) models. Everywhere AI plays a significant role is in access control, user authentication and behaviour analysis, spam, malware, and botnet identification. On the contrary, today's security challenges are numerous. Cloud computing, social media, smart phones, and the widespread usage of numerous programmes such as WhatsApp and Viber have all posed significant security risks to users. This research looks at seven machine learning algorithms: MLP, LSTM, GRU, Decision Tree, SGD, KNN, and CNN. This study uses a two-step efficiency test called AI in Cyber Security. KDD'99 is used in the first step to train the models as well as for testing. Following the NSL-KDD data sets, train models go straight to testing. Following the examination of many cyber-attacks, the research continues on to deep analysis. The effectiveness of all seven AI models is examined, and the outcomes of cyber-attacks are discovered. All of the results have demonstrated the efficacy of using various AI models to perform cyber security. Keywords: Cyber Security, Artificial Intelligence (AI), Machine Learning (ML), KDD’99, NSL-KDD