scholarly journals Implementation of an Embedded Microcontroller-Based Intrusion Detection System

2018 ◽  
Vol 1 (1) ◽  
pp. 27-32
Author(s):  
Philip O Unabor ◽  
Michael S Okundamiya
Keyword(s):  
Liquid Crystal ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Liquid Crystal Display ◽  
Electrical Signal ◽  
Motion Sensor ◽  
Modern Times ◽  
Security Issues

This paper highlights the implementation of an embedded microcontroller-based intrusion detection system. The PIC16F84A microcontroller embedded in the system was programmed using the MikroC Language for the microcontrollers, to pick up an intrusion signal from the motion sensor, (which interprets the signal to be an electrical signal e.g. voltage), process it and then give a command to the display or output units. The output includes a 16x2 ALPHA liquid crystal display (LCD) and a buzzer (alarm unit), which in turn implement the command thereby notifying the environment of the presence of an intruder by displaying “Intruder Detected!” on the LCD and by a beeping sound with an interval of 0.5s delay by the alarm unit. The system was tested and was found to be efficient and suitable for solving myriad of security issues that confront us in modern times.

scholarly journals Multilevel Intrusion Detection System with Affinity Clustering and Ensemble SVM

2020 ◽  
pp. 522-529
Author(s):  
Sadhana Patidar ◽  
Priyanka Parihar ◽  
Chetan Agrawal
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Model Performance ◽  
Feature Reduction ◽  
Support Vector ◽  
Learning Tools ◽  
Security Issues ◽  
Proposed Model

Now-a-days with growing applications over internet increases the security issues over network. Many security applications are designed to cope with such security concerns but still it required more attention to improve speed as well accuracy. With advancement of technologies there is also evolution of new threats or attacks in network. So, it is required to design such detection system that can handle new threats in network. One of the network security tools is intrusion detection system which is used to detect malicious data packets. Machine learning tool is also used to improve efficiency of network-based intrusion detection system. In this paper, an intrusion detection system is proposed with an application of machine learning tools. The proposed model integrates feature reduction, affinity clustering and multilevel Ensemble Support Vector Machine. The proposed model performance is analyzed over two datasets i.e. NSL-KDD and UNSW-NB 15 dataset and achieved approx. 12% of efficiency over other existing work.

scholarly journals Hybrid Intrusion Detection System for Internet of Things (IoT)

2020 ◽  
Vol 2 (4) ◽  
pp. 190-199 ◽  
Author(s):  
Dr. S. Smys ◽  
Dr. Abul Basar ◽  
Dr. Haoxiang Wang
Keyword(s):  
Internet Of Things ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Denial Of Service ◽  
Research Work ◽  
Experimental Result ◽  
Security Issues ◽  
Wide Range ◽  
Conventional Machine

Internet of things (IoT) is a promising solution to connect and access every device through internet. Every day the device count increases with large diversity in shape, size, usage and complexity. Since IoT drive the world and changes people lives with its wide range of services and applications. However, IoT provides numerous services through applications, it faces severe security issues and vulnerable to attacks such as sinkhole attack, eaves dropping, denial of service attacks, etc., Intrusion detection system is used to detect such attacks when the network security is breached. This research work proposed an intrusion detection system for IoT network and detect different types of attacks based on hybrid convolutional neural network model. Proposed model is suitable for wide range of IoT applications. Proposed research work is validated and compared with conventional machine learning and deep learning model. Experimental result demonstrate that proposed hybrid model is more sensitive to attacks in the IoT network.

scholarly journals An Intelligent Feature Selection with Optimal Neural Network Based Network Intrusion Detection System for Cloud Environment

2020 ◽  
Vol 9 (3) ◽  
pp. 3560-3569
Keyword(s):  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Cloud Environment ◽  
Sensitive Data ◽  
High Detection Rate ◽  
Security Issues ◽  
Network Intrusion ◽  
Grasshopper Optimization Algorithm ◽  
Grasshopper Optimization

At present times, Cloud Computing (CC) becomes more familiar in several domains such as education, media, industries, government, and so on. On the other hand, uploading sensitive data to public cloud storage services involves diverse security issues, specifically integrity, availability and confidentiality to organizations/companies. Besides, the open and distributed (decentralized) structure of the cloud is highly prone to cyber attackers and intruders. Therefore, it is needed to design an intrusion detection system (IDS) for cloud environment to achieve high detection rate with low false alarm rate. The proposed model involves a binary grasshopper optimization algorithm with mutation (BGOA-M) as a feature selector to choose the optimal features. For classification, improved particle swarm optimization (IPSO) based NN model, called IPSO-NN has been derived. The significance of the IPSO-NN model is assessed using a set of two benchmark IDS dataset. The experimental results stated that the IPSO-NN model has achieved maximum accuracy values of 99.36% and 97.80% on the applied NSL-KDD 2015 and CICIDS 2017 dataset. The obtained experimental outcome clearly pointed out the extraordinary detection performance of the IPSO-NN model over the compared methods.

scholarly journals Flow Based Intrusion Detection System for Software Defined Networking using Hybrid Machine Learning Technique

2019 ◽  
Vol 9 (2S2) ◽  
pp. 1026-1033
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Software Defined Networking ◽  
Machine Learning Technique ◽  
Security Issues ◽  
Learning Technique ◽  
Flow Information ◽  
Hybrid Machine

Software Defined Networking and OpenFlow protocol have been recently emerged as dynamic and promising framework for future networks. Even though, programmable features and logically centralized controller leads to large number of security issues. To address the security problems, we have to impose Intrusion Detection System module to continuously keep track of the network traffic and to detect the malicious activities in the SDN environment. In this paper, we have implemented flow-based IDS with the help of hybrid machine learning technique. By collecting the flow information from the controller, we classify the traffic, extract the essential features and classify the attack using machine learning based classifier module. For classifier, we have developed hybrid machine learning model with the help of Modified K-Means and C4.5 algorithm. Our proposed work is compared with single machine learning classifier and our experimental results show that, proposed work can classify the normal and attack instances with accuracy of 97.66%.

scholarly journals Penggunaan Metode Signature Based dalam Pengenalan Pola Serangan di Jaringan Komputer

2021 ◽  
Vol 8 (3) ◽  
pp. 517
Author(s):  
Herri Setiawan ◽  
M. Agus Munandar ◽  
Lastri Widya Astuti
Keyword(s):  
Network Security ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Test Results ◽  
Web Based ◽  
Security Issues ◽  
Attack Patterns ◽  
Attack Data ◽  
Tools And Techniques

<p class="Abstrak">Masalah keamanan jaringan semakin menjadi perhatian saat ini. Sudah semakin banyak <em>tools</em> maupun teknik yang dapat digunakan untuk masuk kedalam sistem secara ilegal, sehingga membuat lumpuh sistem yang ada. Hal tersebut dapat terjadi karena adanya celah dan tidak adanya sistem keamanan yang melindunginya, sehingga sistem menjadi rentan terhadap serangan. Pengenalan pola serangan di jaringan merupakan salah satu upaya agar serangan tersebut dapat dikenali, sehingga mempermudah administrator jaringan dalam menanganinya apabila terjadi serangan. Salah satu teknik yang dapat digunakan dalam keamanan jaringan<em> </em>karena dapat mendeteksi serangan secara <em>real time</em> adalah <em>Intrusion Detection System</em> (IDS), yang dapat membantu administrator dalam mendeteksi serangan yang datang. Penelitian ini menggunakan metode <em>signatured based </em>dan mengujinya dengan menggunakan simulasi. Paket data yang masuk akan dinilai apakah berbahaya atau tidak, selanjutnya digunakan beberapa <em>rule</em> untuk mencari nilai akurasi terbaik. Beberapa <em>rule</em> yang digunakan berdasarkan hasil <em>training </em>dan uji menghasilakan 60% hasil <em>training </em>dan 50% untuk hasil uji <em>rule</em> 1, 50% hasil <em>training </em>dan 75% hasil uji <em>rule</em> 2, 75% hasil <em>training</em> dan hasil uji rule 3, 25% hasil <em>training </em>dan hasil uji <em>rule </em>4, 50% hasil <em>training</em> dan hasil uji untuk <em>rule</em> 5. Hasil pengujian dengan metode <em>signatured based</em> ini mampu mengenali pola data serangan melaui protokol TCP dan UDP, dan <em>monitoring </em>yang dibuat mampu mendeteksi semua serangan dengan tampilan <em>web base.</em></p><p class="Abstrak"><em><br /></em></p><p class="Abstrak"><strong><em>Abstract</em></strong></p><p class="Abstract"><em>Network security issues are becoming increasingly a concern these days. There are more and more tools and techniques that can be used to enter the system illegally, thus paralyzing the existing system. This can occur due to loopholes and the absence of a security system that protects it so that the system becomes vulnerable to attacks. The recognition of attack patterns on the network is an effort to make these attacks recognizable, making it easier for network administrators to handle them in the event of an attack. One of the techniques that can be used in network security because of a timely attack is the Intrusion Detection System (IDS), which can help administrators in surveillance that comes. This study used a signature-based method and tested it using a simulation. The incoming data packet will be assessed whether it is dangerous or not, then several rules are used to find the best accuracy value. Some rules used are based on the results of training and testing results in 60% training results and 50% for rule 1 test results, 50% training results and 75% rule 2 test results, 75% training results and rule 3 test results, 25% training results and the result of rule 4 test, 50% of training results and test results for rule 5. The test results with the signature-based method can recognize attack data patterns via TCP and UDP protocols, and monitoring is made to be able to detect all attacks with a web-based display.</em></p><p class="Abstrak"><strong><em><br /></em></strong></p>

scholarly journals Efficient Intrusion Detection Algorithms for Smart Cities-Based Wireless Sensing Technologies

2020 ◽  
Vol 9 (3) ◽  
pp. 39 ◽  
Author(s):  
Rabie A. Ramadan
Keyword(s):  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Smart Cities ◽  
Memory Storage ◽  
Smart Devices ◽  
Security Issues ◽  
Detection Algorithms ◽  
Large Numbers ◽  
New Development

The world is experiencing the new development of smart cities. Smart cities’ infrastructure in its core is based on wireless sensor networks (WSNs) and the internet of things (IoT). WSNs consist of tiny smart devices (Motes) that are restricted in terms of memory, storage, processing capabilities, and sensing and communication ranges. Those limitations pose many security issues where regular cryptography algorithms are not suitable to be used. Besides, such capabilities might be degraded in case cheap sensors are deployed with very large numbers in applications, such as smart cities. One of the major security issues in WSNs that affect the overall operation, up to network interruption, in smart cities is the sinkhole routing attack. The paper has three-fold contributions: (1) it utilizes the concept of clustering for energy saving in WSNs, (2) proposing two light and simple algorithms for intrusion detection and prevention in smart cities—threshold-based intrusion detection system (TBIDS) and multipath-based intrusion detection system (MBIDS), and (3) utilizing the cross-layer technique between the application layer and network layer for the purpose of intrusion detection. The proposed methods are evaluated against recent algorithms—S-LEACH, MS-LEACH, and ABC algorithms.

The Application Research of Data Mining in the Intrusion Detection

2014 ◽  
Vol 644-650 ◽  
pp. 1176-1179
Author(s):  
Feng Lan Liang
Keyword(s):  
Data Mining ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Application Research ◽  
Safety Hazard ◽  
Security Issues ◽  
Network Intrusion ◽  
Detection Technology ◽  
Potential Safety

With the popularization of computer technology and application and popularization, the network technology has been widely used, the resulting network security issues are also increasingly prominent, to the network itself and the information system based on network constitutes the great potential safety hazard. This paper expounds the concept of intrusion detection and data mining, the commonly used invasion detection technology and models, and analyzes the application of data mining technology in intrusion detection system, to provide reference for the optimization and perfection of the network intrusion detection system and using for reference.

A Game-Based Survey for Security Issues in Vehicular Ad Hoc Network

2013 ◽  
Vol 380-384 ◽  
pp. 2427-2430
Author(s):  
Tan Cheng ◽  
Hao Sun ◽  
Ning Cao ◽  
Cheng Li
Keyword(s):  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
Detection System ◽  
Vehicular Ad Hoc Network ◽  
Stable Operation ◽  
Security Issues ◽  
Transmission Success ◽  
Zero Sum

A rapid growth in the number of vehicles contributes to more and more attention on vehicular ad hoc network (VANET) recently, and ensuring security plays a significant role in maintaining its stable operation. Because of some variable environmental factors, its impossible to evaluate a precise value of packets transmission success rate. To reduce the influence of errors on detection, we develop a novel two-person zero-sum intrusion detection game model for formulating confrontation behavior between intrusion detection system (IDS) and malicious node.

scholarly journals Implementing Security in IoT Ecosystem Using 5G Network Slicing and Pattern Matched Intrusion Detection System: A Simulation Study

10.28945/4675 ◽  
2021 ◽  
Vol 16 ◽  
pp. 001-038
Author(s):  
Anshul Jain ◽  
Tanya Singh ◽  
Satyendra Kumar Sharma ◽  
Vikas Prajapati
Keyword(s):  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Network Slicing ◽  
Security Issues ◽  
Main Challenge ◽  
5G Network ◽  
Different Types ◽  
Iot Devices ◽  
Slicing Technology

Aim/Purpose: 5G and IoT are two path-breaking technologies, and they are like wall and climbers, where IoT as a climber is growing tremendously, taking the support of 5G as a wall. The main challenge that emerges here is to secure the ecosystem created by the collaboration of 5G and IoT, which consists of a network, users, endpoints, devices, and data. Other than underlying and hereditary security issues, they bring many Zero-day vulnerabilities, which always pose a risk. This paper proposes a security solution using network slicing, where each slice serves customers with different problems. Background: 5G and IoT are a combination of technology that will enhance the user experience and add many security issues to existing ones like DDoS, DoS. This paper aims to solve some of these problems by using network slicing and implementing an Intrusion Detection System to identify and isolate the compromised resources. Methodology: This paper proposes a 5G-IoT architecture using network slicing. Research here is an advancement to our previous implementation, a Python-based software divided into five different modules. This paper’s amplification includes induction of security using pattern matching intrusion detection methods and conducting tests in five different scenarios, with 1000 up to 5000 devices in different security modes. This enhancement in security helps differentiate and isolate attacks on IoT endpoints, base stations, and slices. Contribution: Network slicing is a known security technique; we have used it as a platform and developed a solution to host IoT devices with peculiar requirements and enhance their security by identifying intruders. This paper gives a different solution for implementing security while using slicing technology. Findings: The study entails and simulates how the IoT ecosystem can be variedly deployed on 5G networks using network slicing for different types of IoT devices and users. Simulation done in this research proves that the suggested architecture can be successfully implemented on IoT users with peculiar requirements in a network slicing environment. Recommendations for Practitioners: Practitioners can implement this solution in any live or production IoT environment to enhance security. This solution helps them get a cost-effective method for deploying IoT devices on a 5G network, which would otherwise have been an expensive technology to implement. Recommendation for Researchers: Researchers can enhance the simulations by amplifying the different types of IoT devices on varied hardware. They can even perform the simulation on a real network to unearth the actual impact. Impact on Society: This research provides an affordable and modest solution for securing the IoT ecosystem on a 5G network using network slicing technology, which will eventually benefit society as an end-user. This research can be of great assistance to all those working towards implementing security in IoT ecosystems. Future Research: All the configuration and slicing resources allocation done in this research was performed manually; it can be automated to improve accuracy and results. Our future direction will include machine learning techniques to make this application and intrusion detection more intelligent and advanced. This simulation can be combined and performed with smart network devices to obtain more varied results. A proof-of-concept system can be implemented on a real 5G network to amplify the concept further.

Sign in / Sign up

Export Citation Format

Share Document