International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
Enhancing Cybersecurity in IoT Networks: Effective Detection of Cyber Attacks Ratnesh K Choudhary, Sonam Chopade, Shraddha Pokale, Rohit Thakur, Goyal Dhakate, Sanskruti Muley Department of Computer Science Engineering, S.B Jain Institute of Technology, Management & Research Nagpur, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The expanding Internet of Things, also known as
tool for detecting cyber threats on the ever-growing network of connected devices [3,4].
the IoT, offers an exciting landscape of networked gadgets, weaving a vast network brimming with potential. However, this exponential growth also casts a long shadow of formidable cybersecurity concerns. Traditional intrusion detection systems (IDS) falter in the face of this rapidly evolving threat landscape and the diverse demands of myriad Iot devices. The sheer heterogeneity of these devices, spanning from simple sensors to intricate smart home appliances, poses a fundamental obstacle. A one-size-fits-all approach crumbles, as resource-constrained devices necessitate lightweight detection mechanisms that tread softly on their limited processing power and memory. Further compounding the challenge is the chameleon-like nature of cyberattacks. Hackers ceaselessly craft new tactics, rendering signature-based detection obsolete. This necessitates intelligent solutions capable of learning and adapting to identify and thwart novel attack patterns. Securing the boundless IoT demands novel cyber defense anomaly detection, AI, and federated learning lead the way.
Fig1: - IoT Health Care The IoT Flock framework is a particularly useful tool for dealing with security concerns in sensitive IoT environments like healthcare [*]. This framework uses ML algorithms to analyse device behaviour, network traffic, and sensor data in real time to identify potential security threats. By finding unusual patterns and suspicious activity, the IoT Flock framework helps healthcare providers take proactive steps to protect their systems and patient data.
Key Words: Cyberattack, IoT Flock, Machine Learning, Attack Detection, IoT Network.
1. INTRODUCTION The Internet of Things (IoT) is quickly growing, creating a web of networked gadgets that pervades every aspect of our lives. While this pervasive connectedness provides unparalleled ease and automation, it also poses a growing cybersecurity threat. Because of the sheer quantity and diversity of these resource-constrained devices, as well as their sensitivity to cyber-attacks, bad actors have a breeding ground. Traditional security solutions, which are frequently intended for high-availability computing settings, fail to adapt to the unique characteristics of the IoT landscape [1, 2].
As the IoT landscape continues to evolve, there will be an even greater need for effective security measures. ML techniques, like those used by the IoT Flock framework, offer a promising way to address the challenges of IoT security, especially in sensitive areas like healthcare. By proactively detecting and responding to cyberattacks, ML-powered security solutions can help maintain the integrity of IoT systems and protect the privacy and well-being of individuals. This study investigates the effectiveness of ML algorithms in protecting the IoT domain by:
This is where machine learning (ML) shines the brightest. Machine learning thrives on large amounts of data. Its capacity to sift through mounds of data, find hidden hints, and continually refresh its knowledge makes it an effective
© 2024, IRJET
|
Impact Factor value: 8.226
1.
|
Creating Robust Defense: We offer a systematic strategy that takes advantage of ML's capabilities. This multi-layered defense starts with thorough
ISO 9001:2008 Certified Journal
|
Page 1364