ITDS | SPMS

ANOMALY DETECTION OF BOTNET IN IOT-BASED CONNECTED DEVICES USING DEEP LEARNING APPROACHES

Project Description
Supervisor

The emergence of the Internet of Things (IoT) concept as a new direction of technological development raises new problems such as valid and timely identification of such devices, security vulnerabilities that can be exploited for malicious activities, and management of such devices. The increased use of IoT infrastructure in these fields has led to the failure of the nodes, increase in threats, attacks, abnormalities, and spying, which is the primary concern and an important domain of an IoT. This study utilized two different datasets from the BoT-IoT and UNSW-NB15 repositories to train the models for anomalies and attacks. In this study, four different deep learning (DL) approaches are used to train the dataset. The models are convolutional neural network (CNN), long short-term memory (LSTM), autoencoders (AEC), and hybrid CNN-LSTM. The CNN, LSTM, AEC and Hybrid CNN-LSTM models achieved accuracies of 0.9785, 0.9698, 0.9050 and 0.9040 respectively. The experimental results revealed that the hybrid achieved the best results on all evaluation metrics whiles maintaining substantial results for the individual models. The models outperformed state-of-the-art (SOTA) in a similar domain. The proposed model can be used as a foundation for monitoring and managing solutions in vast and diverse IoT contexts such as industrial IoT, smart homes, and so on.

Artificial Intelligence: Artificial Intelligence (AI) research in Computer Science and Information Technology explores the development of systems and algorithms that can perform tasks typically requiring human intelligence. These tasks include problem-solving, decision-making, learning, perception, and language understanding. AI research is a vast and interdisciplinary field, encompassing a variety of areas such as machine learning, natural language processing, computer vision, robotics, and cognitive computing. Machine learning (ML) is a core component of AI research. It focuses on creating algorithms that allow computers to learn from data, improve over time, and make predictions or decisions without explicit programming. Subfields of ML include supervised learning, unsupervised learning, reinforcement learning, and deep learning, with applications ranging from image recognition to recommendation systems. Natural language processing (NLP) is another critical area within AI research. It aims to enable machines to understand, interpret, and respond to human language. Researchers in NLP work on tasks like speech recognition, language translation, and sentiment analysis, making it possible for computers to interact with humans in a more natural and intuitive way.