Malware Training Sets

One of the most challenging tasks during Machine Learning processing is to define a great training (and possible dynamic) dataset. Assuming a well known learning algorithm and a periodic learning supervised process what you need is a classified dataset to best train your machine. Thousands of training datasets are available out there, but no great classified datasets for malware analyses exist. This dataset was created to share with the scientific community (and everybody interested on it) in order to give to everyone a base point to start with Machine Learning for Malware Analysis. The collected dataset is composed by the following samples: APT1 292 Samples Crypto 2024 Samples Locker 434 Samples Zeus 2014 Samples机器学习流程中最具挑战性的任务之一，便是构建优质的训练（且可动态更新）数据集。假设已选定成熟的学习算法，并采用周期性有监督学习流程，那么你所需的便是经过分类标注的数据集，以实现机器学习模型的最优训练。目前已有数千款训练数据集可供选用，但适配恶意软件（malware）分析的优质分类数据集仍较为匮乏。本数据集专为共享给科研社群及所有相关领域的感兴趣人士而打造，旨在为所有投身恶意软件分析机器学习研究的人员提供起步基准。本次采集的数据集包含以下样本类型：APT1 292个样本、Crypto 2024个样本、Locker 434个样本、Zeus 2014个样本。