In the field of NetSoftIoT, where network softwarization converges with the proliferation of IoT devices, ensuring robust security in SDN environments is paramount. This paper presents a novel approach that integrates RandomForest for optimized feature selection and LSTM networks for attack detection. Our methodology capitalizes on the LSTM's sequential data processing capability to discern patterns indicative of DDoS attacks within network traffic with an accuracy of 83%. Leveraging a dataset comprising varied traffic types, our model demonstrated precision in identifying DDoS traffic with a recall of 0.94. The results, validated by confusion matrices and classification reports, indicate the model's efficacy in maintaining network integrity against malicious threats. This study advances the frontier of cybersecurity in SDN, crucial for the burgeoning landscape of IoT applications.