With the rapid expansion of the internet and the increasing number of devices connected to the network, the level of cyberattacks has increased significantly. One of the serious threats in this field is Distributed Denial of Service (DDoS) attacks, which use a large number of infected systems to direct a massive volume of traffic towards specific targets. The distributed and scalable nature of these attacks makes detecting and defending against them considerably more difficult than other security threats. In recent years, various models have been developed to detect these types of attacks, but many of them face challenges in accurate detection or reducing the error rate. To address this issue, this paper proposes an intrusion detection system based on deep neural networks and an attention mechanism. The proposed method was implemented using the Python programming language and the PyTorch library and tested on the CICIDS2017, CICIDS2018, and CICDDoS2019 datasets. The results showed that the proposed model outperforms previous methods in detecting DDoS attacks and significantly reduces the false positive rate. These results indicate the potential of the proposed method in enhancing network security and providing an effective solution against cyber threats.