Deep Learning Techniques for Anomaly Detection in Cloud Computing

Santosh, Serena (2024) Deep Learning Techniques for Anomaly Detection in Cloud Computing. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (755kB) | Preview

Abstract

Cloud computing, which enables on-demand access of computing resources over the internet, is a paradigm that is undergoing a lot of changes. With a lot of organisations shifting to cloud, there is a vast amount of data and resources in cloud, which needs to be protected. This research proposes the usage of GRU-BERT (Gated Recurrent Unit - Bidirectional Encoder Representations from Transformers) model with self-attention mechanism to detect anomalous behaviour in cloud which is essential to increase the resiliency of the cloud. The possibility of using autoencoders with self-healing mechanism is also discussed in this research. The aim of this project is to implement a solution that can increase the security in cloud with increased performance in terms of cost, computational complexity, execution time, and energy consumption. GRU-BERT model was evaluated based on performance metrics and it outperformed LSTM (Long Short-Term Memory) in terms of cost by 46.55%. Optimisation of NAB (Numenta Anomaly Benchmark) by making use of standard performance metrics for evaluation generated better results with regards to reducing the false negatives. Bayesian optimisation technique was utilised to optimise the hyperparameters in GRU-BERT. This technique was implemented using Hyperopt, producing great results with increased overall performance in terms of validation loss.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Samarawickrama, Yasantha UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	16 Jul 2025 11:50
Last Modified:	16 Jul 2025 11:50
URI:	https://norma.ncirl.ie/id/eprint/8150

Actions (login required)

View Item