With the rapid digitization of services, network traffic has surged, leading to increased cybersecurity risks such as Distributed Denial of Service (DDoS) and zero-day attacks. Zero-day attacks are particularly dangerous as they exploit unknown vulnerabilities and often bypass traditional Intrusion Detection Systems (IDS). While Deep Learning (DL)-based IDSs can automatically learn features without manual signature extraction, they often struggle to detect zero-day attacks, especially those with complex data patterns. Recently, hybrid DL approaches have shown promise by learning from historical network behavior to better identify such advanced threats. Thus, this research developed a Wide Residual Quantum Dilated Convolutional Neural Network for zero-day attack detection. In the training phase, the input target and source domains are passed to the Manifold alignment, and the outcome acquired is the transformed source and target domains. Then, Deep Fuzzy Clustering is utilized to cluster the transformed source domain. Furthermore, the clustered source domain and transformed target domain are applied over the Manhattan distance to generate labelled source and soft-labelled target data and are utilized for training the Wide Residual Quantum Dilated Convolutional Neural Network model to detect zero-day attacks. In the testing phase, zero-day attack detection is conducted to determine whether the attack is normal or a zero-day attack by utilizing a Wide Residual Quantum Dilated Convolutional Neural Network. The devised Wide Residual Quantum Dilated Convolutional Neural Network has gained superior performance with a True Negative Rate of 91.27 %, True Positive Rate of 91.79 %, accuracy of 91.57 %, F-measure of 90.18 %, and Precision of 90.81 %.