| Autor: |
Panjaitan, Muktar Bahruddin, Sivakumar, Janaki, Chabra, Archana, James, Menila, Kaur, Harpreet, Vaid Kwatra, Chetna |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2023, Vol. 2930 Issue 1, p1-9, 9p |
| Abstrakt: |
As of the exponential increase in the use of computer networks, there are now problems associated with maintaining the network's availability, integrity, and secrecy. Because of this, network administrators have no choice but to implement a wide variety of intrusion detection systems (IDS), which are designed to assist in monitoring network traffic to identify unauthorized and hostile actions. A security policy violation with the intention to harm is known as an intrusion. As a result, an intrusion detection system will monitor the traffic moving through computer systems on a network to check for malicious actions and known dangers. When it discovers such threats, the system will send up an alarm. There are two types of attacks that can be identified by an intrusion detection system: signature-based detection and misuse detection. In signature-based detection, an IDS uses information gathered from a database to analyze and compare the attack signatures to those that have been saved. The second type of detection is called anomaly detection, which considers the likelihood of a particular action happening outside the typical pattern of behavior. This paper aims to provide an overview of the various efforts being carried out to develop an effective IDS using machine learning and deep learning. The results of the study will be used to evaluate the performance of different classifiers. In addition, the paper also presents the results of the various studies that were carried out. These findings will be used to develop further improvements and enhance the performance of the IDS. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
