A Comprehensive Analysis of Secure Attack Detection on Virtual Machines in Cloud Computing

Cloud computing provides various computing services including processing power, storage, networking, software, analytics, and databases. A Virtual Machine (VM) is a software-based simulation of a physical computer that runs an operating system and applications. The VM can run multiple functions on a single physical machine. Secure attack detection on VMs utilizes implementation techniques to detect and monitor malicious activities in the cloud environment. This detection involves Intrusion Detection Systems (IDS), anomaly detection methods, and real-time monitoring tools that analyse network traffic, system logs, and user behaviour. Optimization techniques are used to enhance the efficiency of the detection models. Swarm-based algorithms such as Intelligent Water Drop (IWD), Enhanced Shark Smell Optimization Algorithm (ESSOA), Brownian movement-centered gravitation search algorithm (BMGSA), Dual Conditional Moth Flame Algorithm (DC-MFA), Bat Optimization Algorithm (BOA), and Ant Colony Algorithm (ACO) are employed for this purpose. Additionally, Evolution-based algorithms such as Multi-objective Whale Optimization algorithm-based Differential Evolution (M-WODE), Gene Expression Programming (GEP), Genetic Algorithm (GA), and DragonFly-based Genetic Deep Belief Network (DGDBN) have also been used for anomaly detection. The performance metrics of makespan, energy consumption, Degree of Imbalance (DOI), and execution cost are used to evaluate these approaches.