Multi-fidelity surrogate modeling offers a cost-effective approach to reduce extensive evaluations of expensive physics-based simulations for reliability predictions. However, considering spatial uncertainties in multi-fidelity surrogate modeling remains extremely challenging due to the curse of dimensionality. To address this challenge, this paper introduces a deep learning-based multi-fidelity surrogate modeling approach that fuses multi-fidelity datasets for high-dimensional reliability analysis of complex structures. It first involves a heterogeneous dimension transformation approach to bridge the gap in terms of input format between the low-fidelity and high-fidelity domains. Then, an explainable deep convolutional dimension-reduction network is proposed to effectively reduce the dimensionality of the structural reliability problems. To obtain a meaningful low dimensional space, a new knowledge reasoning-based loss regularization mechanism is integrated with the covariance matrix adaptation evolution strategy to encourage an unbiased linear pattern in the latent space for reliability predictions. Then, the high-fidelity data can be utilized for bias modeling using Gaussian process regression. Finally, Monte Carlo simulation is employed for the propagation of high-dimensional spatial uncertainties. Two structural examples are utilized to validate the effectiveness of the proposed method.