This paper explores the investigation of Firefly and Grey Wolf Optimization (GWO) nature-inspired algorithms to enhance phishing detection within the cloud security landscape. The study seeks to take advantage of the power of machine learning classifiers, such as Decision Trees, Random Forests, Support Vector Machines, and Neural Networks, and optimize their performance using Firefly and GWO algorithms. The research methodology comprises multiple stages, including data collection and preprocessing, feature engineering, machine learning model selection, integration of optimization algorithms, model parameter tuning, and rigorous evaluation. By employing optimization algorithms, the study aims to enhance feature selection and hyperparameter optimization, thus increasing the classification accuracy of machine learning models. This research holds the promise of more resilient phishing detection systems capable of adapting to the dynamic nature of phishing campaigns in cloud environments. The results and insights gleaned from this research can significantly contribute to reinforcing cloud security, safeguarding sensitive data, and fortifying organizations against the malicious threat of phishing attacks. The findings offer a glimpse into the ever-advancing field of cybersecurity, where the synergy between machine learning and optimization nature-based algorithms emerges as a formidable defense against an ever-evolving cyber menace.