Currently, phishing attacks are posing great damage to the online community. As traditions, attack detection strategies are not effective against this new type of threat. Hence, there is a need for advanced attack detection techniques. In this context, this research proposed a hybrid deep learning and big data-based technique for phishing attack detection approach. Our proposed approach used Conv2d layers in sequence for analysis of the incoming traffic and predict its behavior. We used different parameters to measure our proposed approach. Through the use of the cuckoo optimization algorithm, the propsed approach achieves a high accuracy of 92%.