anonymizeddb/MCAD-CIC-3x1

MCAD-CIC-3x1是一个用于网络入侵检测的多源持续异常检测基准场景。它将三个CIC系列源数据集（cicids2017、cicids2018和cicunsw）结合成一个三任务持续学习场景，每个任务对应一个整合的源数据集。该基准旨在评估跨源分布偏移下的持续异常检测方法。数据集包含17,915,569个样本，测试集中报告的异常比例为10.42%。数据集已为双盲NeurIPS评审进行匿名化处理，作者姓名、机构归属、项目致谢和非匿名论文引用已被有意省略。MCAD-CIC-3x1 is a multi-source continual anomaly detection benchmark scenario for network intrusion detection. It combines three CIC-family source datasets into a three-task continual-learning scenario: 1. cicids2017, 2. cicids2018, 3. cicunsw. Each task corresponds to one consolidated source dataset. The benchmark is designed to evaluate continual anomaly detection methods under cross-source distribution shift. The dataset contains 17,915,569 samples and has a reported 10.42% anomaly ratio in the test set. The dataset is anonymized for double-blind NeurIPS review. Author names, institutional affiliations, project acknowledgements, and non-anonymous paper references are intentionally omitted.