In the last ten years, the IoT has played a crucial role in society’s digital transformation. However, because of the wide range of devices it encompasses, it is also facing increased security vulnerabilities. This research presents a novel mechanism called the Self-attention-based 1D-CNN-LSTM, which uses Convolutional Neural Networks (CNNs) combined with a Long Short-Term Memory (LSTM) model enhanced with a Self-Attention mechanism for detecting IoT attacks. The proposed mechanism achieves high accuracy and efficiently differentiates malicious and benign network traffic. By employing Shapley Additive Explanations (SHAP), we identified important predictive features from the preprocessed data, which were retrieved using CICFlowmeter. This has strengthened the dependability of the model. In addition, we enhanced the model by training it on a smaller collection of features, resulting in shorter training time while preserving accuracy. We have also generated nine augmented IoT tabular datasets named CIC-BCCC-NRC_TabularIoTAttack-2024 from accessible IoT datasets to evaluate the model’s robustness and showcase its efficacy in IoT security.