Monitoring network traffic data to detect any hidden patterns of anomalies is\na challenging and time-consuming task that requires high computing resources.\nTo this end, an appropriate summarization technique is of great importance,\nwhere it can be a substitute for the original data. However, the summarized\ndata is under the threat of removing anomalies. Therefore, it is vital to\ncreate a summary that can reflect the same pattern as the original data.\nTherefore, in this paper, we propose an INtelligent Summarization approach for\nIDENTifying hidden anomalies, called INSIDENT. The proposed approach guarantees\nto keep the original data distribution in summarized data. Our approach is a\nclustering-based algorithm that dynamically maps original feature space to a\nnew feature space by locally weighting features in each cluster. Therefore, in\nnew feature space, similar samples are closer, and consequently, outliers are\nmore detectable. Besides, selecting representatives based on cluster size keeps\nthe same distribution as the original data in summarized data. INSIDENT can be\nused both as the preprocess approach before performing anomaly detection\nalgorithms and anomaly detection algorithm. The experimental results on\nbenchmark datasets prove a summary of the data can be a substitute for original\ndata in the anomaly detection task.\n