A Review on Machine Learning Techniques in Addressing Cloud Security Issues

Cloud Computation (CC) provides on-demand access to network resources, combining Both publicly and privately owned servers to offer users a single, Internet-based ecosystem. Edge computation enhances response times and reduces bandwidth usage by bringing computation and storage closer to users. Mobile Cloud Computation (MCC) extends this by delivering applications to mobile gadgets. However, both CC and Edge computation face safety challenges, including vulnerabilities in user data and network connections, limiting their adoption. Machine learning (ML) offers potential solutions to these issues. The review explores various ML techniques—reinforcement learning, unsupervised, supervised and semi-supervised used for the purpose of addressing cloud safety concerns and comparing their features, strengths, and limitations. It also identifies future research opportunities to improve cloud safety.