Phishing attacks pose a severe cybersecurity threat, often bypassing traditional Intrusion Detection Systems (IDS) due to high false positives and low detection accuracy. This study enhances phishing detection by integrating nature-inspired metaheuristic algorithms with machine learning. Support Vector Machine (SVM) performance is optimized using Grey Wolf Optimizer (GWO), Firefly Algorithm, Bat Algorithm, and Whale Optimization Algorithm, mimicking natural behaviours for improved efficiency. Experimental evaluation shows that our model outperforms traditional methods, achieving over 95% detection accuracy while significantly reducing false positives, making it a more adaptive and intelligent phishing detection system.