DDoS attack effect evaluation is the basis of security strategy deployment. The traditional effect evaluation method relies on the original data, ignoring the relationship between features and the evaluation target and indicator data redundancy, which affects the accuracy and reliability of the evaluation result. To this end, we introduce distance entropy to measure the similarity between features and evaluation target and use LSTM and Triplet networks to measure multiple correlations simultaneously. Then, a 2D-CNN is used to mine deep feature information and filter irrelevant information. We also combine 1D-CNN and attention models to achieve hierarchical sampling of different local features. Finally, three fully connected layers’ training obtains a total evaluation value. We conducted experiments on five commonly used DDoS datasets. The results showed that the average ranking accuracy of the neural network-based DDoS attack evaluation method (NNDE) reached 87.2%, 91.3%, 88%, 85.6%, and 94.5%, respectively. Compared with other evaluation methods, an average increase of 19.73% indicates that this method can better evaluate the effect of DDoS attacks.