Issuu

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 09 Issue: 06 | June 2022

p-ISSN: 2395-0072

www.irjet.net

MACHINE LEARNING AND DEEP LEARNING MODEL-BASED DETECTION OF IOT BOTNET ATTACKS. Anuja Lakhe1, Sunilkumar Jaiswal2 M.tech, Department of Computer Science and Engineering, MGM university, Jawaharlal Nehru Engineering College, Aurangabad, India Assistant Professor, Department of Computer Science and Engineering, MGM university, Jawaharlal Nehru Engineering College, Aurangabad, India -------------------------------------------------------------------------***---------------------------------------------------------------------Botnets are generally assembled to affect as many devices Abstract- Computers and networks have been under threat

as possible and more complex botnets even self-regard and update their behavior, finding and affecting devices accordingly. An IoT botnet is a grid of devices connected to the internet of things (IoT), typically routers, that have been affected by malware and have collapsed under the control of malicious actors.[5] IoT botnets are known for being used in immersing distributed denial-of-service (DDoS) attacks on target entities to disturb their operations and services. Distributed Denial of Service (DDoS) attack is the most common significant threat to online service providers. It involves the attacker’s ability to negotiate the availability of web services offered by the targeted host. This is achieved by using attacking agents such as botnet and or compromised Internet of Things (IoT) devices to exhaust the victim’s computing capacity (Network Bandwidth, System and Application resources) preventing service availability to legitimate users. There are many techniques that as Machine Learning, Deep Learning, etc., to detect DDoS attacks. Of these techniques, the Deep learning technique is more suitable to detect DDoS attacks.

from viruses, worms, and attacks from hackers since they were first used. In 2018, the number of devices connected to the Internet exceeded the number of human beings and this increasing trend will see about 80 billion devices by 2024. Securing these devices and the data passing between them is a challenging task because the number of IoT Botnet attacks is also increasing sharply year by year. To address this issue, a large number of defenses against network attacks have been proposed in the literature. Despite all the efforts made by researchers in the community over the last two decades, the network security problem is not completely solved. In general, defense against network attacks consists of preparation, detection, and reaction phases. The core element of a good defense system is an IoT Botnet Attack Detection System (IBA-DS), which provides proper attack detection before any reaction. An IBA-DS aims to detect IBAs before they seriously damage the network. The term IBA refers to any unauthorized attempt to access the elements of a network with the aim of making the system unreliable.

Key words: IoT Botnet, Distributed Denial of Service, Machine Learning, Deep Learning, the Detection system

A detection system continuously checks network traffic and signals any developing attacks in the network. This should then generate a response mechanism that will solicit to assure the network resources and maintain a satisfactory level of quality of service for the genuine users. The success of a detection mechanism is determined by its probability of correct detection, false alarm, and missed detection, and its ability to reach detection decisions quickly in real-time and consume minimal processing resources.[1].

1. INTRODUCTION In today’s hasty world, one cannot think of life without the internet. Internet is required in different fields like education, business, shopping, communication, etc. Despite many advantages, many evils have been generated over the internet, especially which leads to miscommunication, attacks, hacking, etc. In recent times, the Internet of Things (IoT) is very fast developing with many devices that are convenient in the smart home, smart city, and many other smart systems for education, organization, etc. But there is indeed malware that is targeting the IoT devices. Accordingly, it is necessary to design or develop systems effective for the detection of such types of malwares.

Impact Factor value: 7.529

The paper is organized into five sections. The current section is about the challenges of botnet attacks and the detection systems. In section 2 the Literature Survey of the botnet-attack detections researches will be addressed. Furthermore, in section 3 methodology will be presented.

ISO 9001:2008 Certified Journal

Page 3166