This paper presents a novel Network Intrusion Detection System (NIDS) algorithm based on the Transformer model, tailored for cloud environments. The algorithm integrates the fundamental aspects of network intrusion detection with the sophisticated attention mechanism of the Transformer model, enhancing the accuracy of detecting various intrusion types. The design and implementation of the algorithm are detailed, including data preprocessing, model training, and label prediction. The experimental results, conducted using the CIC-IDS 2018 dataset, demonstrate that the proposed model achieves an accuracy of over 93%, comparable to that of the CNN-LSTM model. The paper also discusses the contributions of the work, the related research, and the experimental setup, highlighting the effectiveness and viability of the Transformer-based NIDS in cloud security. Future work includes integrating Graph Neural Networks to improve the model's ability to identify complex intrusion patterns in distributed environments.This paper presents a novel Network Intrusion Detection System (NIDS) algorithm based on the Transformer model, tailored for cloud environments. The algorithm integrates the fundamental aspects of network intrusion detection with the sophisticated attention mechanism of the Transformer model, enhancing the accuracy of detecting various intrusion types. The design and implementation of the algorithm are detailed, including data preprocessing, model training, and label prediction. The experimental results, conducted using the CIC-IDS 2018 dataset, demonstrate that the proposed model achieves an accuracy of over 93%, comparable to that of the CNN-LSTM model. The paper also discusses the contributions of the work, the related research, and the experimental setup, highlighting the effectiveness and viability of the Transformer-based NIDS in cloud security. Future work includes integrating Graph Neural Networks to improve the model's ability to identify complex intrusion patterns in distributed environments.