Breast tumors have become one of the most frequent illnesses among women, with 287,850 new cases projected to be discovered in 2022. Of those, 43,250 women passed away from this malignancy. The mortality rate for cancer might be decreased through early detection. Despite this, employing mammography photographs to manually identify this kind of cancer is a challenging process that always demands an expert. In the literature, a number of AI-based (Artificial Intelligence) strategies have been proposed. However, they still deal with issues including irrelevant feature extraction, inadequate training models, and similarities between cancerous and non-cancerous areas. In order to identify breast cancer, this research suggested an SMO-MAFNet-Hybrid Alexnet model. The images in this study were first preprocessed to get rid of noise. After that, the multi-attention fusion network (MAFNet) is used to extract features. The Spider Monkey Optimization (SMO) method is utilized in this work to optimize the learning rate in MAFNet. Following feature extraction, classification is done using the AlexNet model. In this work, hybrid optimization, namely Ant Colony Optimization-Reptile Search Algorithm (ACO-RSA), is applied to fine-tune the hyperparameters in AlexNet classification. The suggested method was tested using the CBIS-DDSM (Curated breast imaging subset of Digital Database for Screening Mammography) dataset and demonstrated an accuracy of 98%, outperforming previous models.