In the contemporary era, the exponential growth of data has elevated the importance of information security and data analysis systems within the realm of Big Data. Intrusion Detection Systems (IDS) serve as crucial tools for monitoring and analyzing data to identify potential intrusions in network environments. However, traditional IDS models face challenges in coping with the sheer volume, diversity, and velocity of big data. This paper introduces a novel approach, the Quantum Brain Storm Optimization (QBSO)-based Feature Selection with Fuzzy Deep Neural Network (FDNN), referred to as the QBSO-FDNN model, tailored for Intrusion Detection Systems in big data environments. The proposed model aims to enhance intrusion detection capabilities within the context of big data. The methodology involves preprocessing steps to improve the quality of the big data. Additionally, to alleviate computational complexity, the QBSO algorithm is employed to select an optimal set of features. The selection of these optimal features through the QBSO algorithm contributes to improved detection performance. Furthermore, the FDNN model serves as a classification mechanism to identify occurrences of intrusions within the network. The effectiveness of the QBSO-FDNN model is evaluated through an extensive set of simulations conducted on benchmark datasets. The experimental results demonstrate the superior performance of the proposed model, achieving a detection accuracy of 98.90%. In summary, the QBSO-FDNN model presented in this paper addresses the shortcomings of traditional IDS models in handling the challenges posed by big data. The integration of quantum-inspired feature selection and a fuzzy deep neural network showcases promising results, making it a noteworthy contribution to the field of intrusion detection in the context of large-scale data environments.