scholarly journals Intrusion Detection Framework Using Efficient Spectral Clustering Technique

2020 ◽  
Author(s):  
K. Vengatesan ◽  
Abhishek Kumar ◽  
K. Harish Eknath ◽  
Sayyad Samee ◽  
Rajiv Vincent ◽  
...  
Keyword(s):  
Intrusion Detection ◽  
Cyber Security ◽  
Intrusion Detection System ◽  
Spectral Clustering ◽  
Detection System ◽  
Security Threats ◽  
Data Set ◽  
Rule Based ◽  
Clustering Technique ◽  
Irregular Data

Developing cyber-security threats are an industrious test for system managers and security specialists as new malware is persistently cleared. Attackers may search for vulnerabilities in commercial items or execute advanced surveillance crusades to comprehend an objective’s network and assemble data on security items like firewalls and intrusion detection/avoidance systems (network or host-based). Numerous new assaults will in general be changes of existing ones. In such a situation, rule-based systems neglect to detect the assault, despite the fact that there are minor contrasts in conditions/credits between rules to distinguish the new and existing assault. To detect these distinctions the IDS must have the option to disconnect the subset of conditions that are valid and foresee the feasible conditions (not the same as the first) that must be watched. We have given various techniques to detect intrusions (or anomalies) which are dissipated consistently and structure little clusters of irregular data. To improve the clustering results, the dissipated anomalies are detected and expelled before agent clusters are framed utilizing SC (spectral clustering). For assessment, a manufactured and genuine data set are utilized and our outcomes show that the utilization of SC (spectral clustering) is a promising way to deal with the advancement of an Intrusion Detection System.

Development of Intrusion Detection System for Security Threats in Internet of Things Using Artificial Neural Network

2019 ◽  
Vol 16 (8) ◽  
pp. 3242-3245
Author(s):  
R. Ramadevi ◽  
N. R. Krishnamoorthy ◽  
D. Marshiana ◽  
Sujatha Kumaran ◽  
N. Aarthi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Internet Of Things ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Denial Of Service ◽  
Security Threats ◽  
Data Set ◽  
Artificial Neural

Internet of things (IoT) is a revolutionary technology which changes our life and work. Many industry sectors such as manufacturing, transportation, utilities, health care, consumer electronics and automobiles are invested and adopted towards IoT technology. The major inconvenience with IoT is its safety, as it is prone to attack by hackers. Detection Systems are used to detect these intrusions to protect the information and communication systems. Hence it is essential to design an intrusion detection system for security threats of IoT networks. This paper focuses, on the development of Artificial Neural Network (ANN) based Intrusion Detection System for threat analysis in IoT network. KDD-99 data set with Denial of Service (DoS) type attack is used to train and test three different ANN models. In this research, a Feed Forward Back Propagation (FFBP) network is used to detect the DoS attack. The process of optimization of a FFBP network involves comparison of classification accuracy during both training and testing in terms of true positive and false positive rates. For the data set considered the optimised network has achieved 100% efficiency during both training and testing.

scholarly journals To Decrease the Issue of False Alarm Rate by Providing Authentication & Thus Improving the Efficiency of Intrusion Detection System by Comparing the Result of Filtered Clusterer Algorithm & Make-Density Based Clustering Algorithm without Attribute Count

2021 ◽  
Vol 10 (1) ◽  
pp. 110-120
Author(s):  
Pratik Jain* ◽  
Ravikant Kholwal ◽  
Muskan Patidar
Keyword(s):  
Intrusion Detection ◽  
Cyber Security ◽  
False Positive ◽  
Intrusion Detection System ◽  
Clustering Algorithm ◽  
Detection System ◽  
Data Set ◽  
Average Data ◽  
Density Based Clustering ◽  
The One

The Intrusion Detection System sends alerts when it detects doubtful activities while monitoring the network traffic and other known threats. In today’s time in the field of Cyber security Intrusion Detection is considered a brilliant topic that could be objective. But it might not remain objectionable for a longer period. For understanding Intrusion Detection, the meaning of Intrusion must be clear at first. According to the oxford’s learners dictionary “Intrusion is the act of entering a place that is private or where you may not be wanted”. For this article, here it defines intrusion as any un-possessed system or network festivity on one (or more) computer(s) or network(s). Here is the example of a faithful user trying to access the system taking more than the usual trial counts to complete his access to the particular account or trying to connect to an unauthorized remote port of a server. The ex-employee who was being fired lately can provoke intrusion or any authentic worker can also provoke intrusion or any other person from the outside world could perform it. In this clause, the average data is found as the attack which is considered as the case of false positive. In this paper, the main focus is on the illustration and a solution offered for the same problem. Here we are using the KDD CUP 1999 data set. According to the outcome, the anomaly class is the one that has a higher number of counts than this class. Even if it is the true user trying to get access but the outcome is an anomaly due to the high number of counts in the class. This paper introduces a solution for the detection of a true person and eradicates the false positive.

An integrated rule based intrusion detection system: analysis on UNSW-NB15 data set and the real time online dataset

2019 ◽  
Vol 23 (2) ◽  
pp. 1397-1418 ◽  
Author(s):  
Vikash Kumar ◽  
Ditipriya Sinha ◽  
Ayan Kumar Das ◽  
Subhash Chandra Pandey ◽  
Radha Tamal Goswami
Keyword(s):  
Intrusion Detection ◽  
Real Time ◽  
Intrusion Detection System ◽  
System Analysis ◽  
Detection System ◽  
Data Set ◽  
Rule Based ◽  
The Real

scholarly journals DCNN-IDS : Deep Convolutional Neural Network based Intrusion Detection System

2020 ◽  
Author(s):  
Sriram Srinivasan ◽  
Shashank A ◽  
vinayakumar R ◽  
Soman KP
Keyword(s):  
Neural Network ◽  
Intrusion Detection ◽  
Convolutional Neural Network ◽  
Intrusion Detection System ◽  
Input Data ◽  
Detection System ◽  
Deep Convolutional Neural Network ◽  
Traffic Data ◽  
Data Set ◽  
Research Problems

In the present era, cyberspace is growing tremendously and the intrusion detection system (IDS) plays a key role in it to ensure information security. The IDS, which works in network and host level, should be capable of identifying various malicious attacks. The job of network-based IDS is to differentiate between normal and malicious traffic data and raise an alert in case of an attack. Apart from the traditional signature and anomaly-based approaches, many researchers have employed various deep learning (DL) techniques for detecting intrusion as DL models are capable of extracting salient features automatically from the input data. The application of deep convolutional neural network (DCNN), which is utilized quite often for solving research problems in image processing and vision fields, is not explored much for IDS. In this paper, a DCNN architecture for IDS which is trained on KDDCUP 99 data set is proposed. This work also shows that the DCNN-IDS model performs superior when compared with other existing works.

scholarly journals IntruDTree: A Machine Learning-Based Cyber Security Intrusion Detection Model

2020 ◽  
Author(s):  
Iqbal H. Sarker ◽  
Yoosef B. Abushark ◽  
Fawaz Alsolami ◽  
Asif Irshad Khan
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Cyber Security ◽  
Intrusion Detection System ◽  
Detection System ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Security Model ◽  
K Nearest Neighbor ◽  
Detection Model

Cyber security has recently received enormous attention in today’s security concerns, due to the popularity of the Internet-of-Things (IoT), the tremendous growth of computer networks, and the huge number of relevant applications. Thus, detecting various cyber-attacks or anomalies in a network and building an effective intrusion detection system that performs an essential role in today’s security is becoming more important. Artificial intelligence, particularly machine learning techniques, can be used for building such a data-driven intelligent intrusion detection system. In order to achieve this goal, in this paper, we present an Intrusion Detection Tree (“IntruDTree”) machine-learning-based security model that first takes into account the ranking of security features according to their importance and then build a tree-based generalized intrusion detection model based on the selected important features. This model is not only effective in terms of prediction accuracy for unseen test cases but also minimizes the computational complexity of the model by reducing the feature dimensions. Finally, the effectiveness of our IntruDTree model was examined by conducting experiments on cybersecurity datasets and computing the precision, recall, fscore, accuracy, and ROC values to evaluate. We also compare the outcome results of IntruDTree model with several traditional popular machine learning methods such as the naive Bayes classifier, logistic regression, support vector machines, and k-nearest neighbor, to analyze the effectiveness of the resulting security model.

Enhance Network Intrusion Detection System by Exploiting BR Algorithm as an Optimal Feature Selection

2015 ◽  
pp. 17-32 ◽  
Author(s):  
Soukaena Hassan Hashem
Keyword(s):  
Intrusion Detection ◽  
Wireless Network ◽  
Intrusion Detection System ◽  
Missing Values ◽  
Detection System ◽  
Network Intrusion Detection ◽  
Wireless Data ◽  
Data Set ◽  
Network Intrusion ◽  
Network Intrusion Detection System

This chapter aims to build a proposed Wire/Wireless Network Intrusion Detection System (WWNIDS) to detect intrusions and consider many of modern attacks which are not taken in account previously. The proposal WWNIDS treat intrusion detection with just intrinsic features but not all of them. The dataset of WWNIDS will consist of two parts; first part will be wire network dataset which has been constructed from KDD'99 that has 41 features with some modifications to produce the proposed dataset that called modern KDD and to be reliable in detecting intrusion by suggesting three additional features. The second part will be building wireless network dataset by collecting thousands of sessions (normal and intrusion); this proposed dataset is called Constructed Wireless Data Set (CWDS). The preprocessing process will be done on the two datasets (KDD & CWDS) to eliminate some problems that affect the detection of intrusion such as noise, missing values and duplication.

Sign in / Sign up

Export Citation Format

Share Document