The custom mobile dataset, named DoH-Mobile-Traffic, was specifically collected using the RethinkDNS tool. This dataset, with a total size of 38.21 GB, includes 289,475 normal flows and 1,711 encrypted DoH flows from multiple DoH service providers, including 360 DNS, Alidns, and Tencent Dnspod. The dataset captures a diverse range of DoH traffic from mobile devices, providing a valuable resource for testing and evaluating DoH detection systems in real-world network environments.If you find this dataset helpful, pelase cite: @article{ZUO2025103125, title = {METC: A Hybrid Deep Learning Framework for Cross-Network Encrypted DNS over HTTPS Traffic Detection and Tunnel Identification}, journal = {Information Fusion}, volume = {121}, pages = {103125}, year = {2025}, issn = {1566-2535}, doi = {https://doi.org/10.1016/j.inffus.2025.103125}, url = {https://www.sciencedirect.com/science/article/pii/S1566253525001988}, author = {Ming Zuo and Changyong Guo and Haiyan Xu and Zhaoxin Zhang and Yanan Cheng}, keywords = {DNS over HTTPS (DoH), Encrypted Traffic Detection, Tunnel Identification, Deep Learning, Machine Learning, Network Security}, }