Authcode - Dataset

Intending to cover the existing gap regarding behavioral datasets modelling interactions of users with individual a multiple devices in Smart Office to later authenticate them continuously, we publish the following collection of datasets, which has been generated after having five users interacting for 60 days with their personal computer and mobile devices. Below you can find a brief description of each dataset.Dataset 1 (2.3 GB). This dataset contains 92975 vectors of features (8096 per vector) that model the interactions of the five users with their personal computers. Each vector contains aggregated data about keyboard and mouse activity, as well as application usage statistics. More info about features meaning can be found in the readme file. Originally, the number of features of this dataset was 24 065 but after filtering the constant features, this number was reduced to 8096. There was a high number of constant features to 0 since each possible digraph (two keys combination) was considered when collecting the data. However, there are many unusual digraphs that the users never introduced in their computers, so these features were deleted in the uploaded dataset.Dataset 2 (8.9 MB). This dataset contains 61918 vectors of features (15 per vector)that model the interactions of the five users with their mobile devices. Each vector contains aggregated data about application usage statistics. More info about features meaning can be found in the readme file.Dataset 3 (28.9 MB). This dataset contains 133590vectors of features (42 per vector)that model the interactions of the five users with their mobile devices. Each vector contains aggregated data about the gyroscope and Accelerometer sensors.More info about features meaning can be found in the readme file.Dataset 4 (162.4 MB). This dataset contains 145465vectors of features (241 per vector)that model the interactions of the five users with both personal computers and mobile devices. Each vector contains the aggregation of the most relevant features of both devices. More info about features meaning can be found in the readme file.Dataset 5 (878.7 KB). This dataset is composed of 7 datasets. Each one of them contains an aggregation of feature vectors generated from the active/inactive intervals of personal computers and mobile devices by considering different time windows ranging from 1h to 24h.1h: 4074 vectors2h: 2149 vectors3h: 1470 vectors4h: 1133 vectors6h: 770 vectors12h: 440 vectors24h: 229 vectors

为填补当前智能办公场景下用户与多台个人设备交互行为建模数据集的空白，以实现后续的持续身份认证，我们发布如下数据集集合。该数据集由5名用户在60天内使用个人计算机与移动设备的交互行为生成。
以下为各数据集的简要说明：
数据集1（2.3 GB）：该数据集包含92975条特征向量（feature vector），每条向量含8096个特征，用于建模5名用户与个人计算机的交互行为。每条向量整合了键盘、鼠标活动及应用使用统计数据。特征含义的详细说明可参见自述文件。该数据集初始特征总数为24065，经过滤恒定特征后缩减至8096。由于数据采集阶段考虑了所有可能的双键组合（digraph），大量恒定特征的取值为0；但用户实际未输入过诸多异常双键组合，因此在本上传数据集中已将此类特征移除。
数据集2（8.9 MB）：该数据集包含61918条特征向量（feature vector），每条向量含15个特征，用于建模5名用户与移动设备的交互行为。每条向量整合了应用使用统计数据。特征含义的详细说明可参见自述文件。
数据集3（28.9 MB）：该数据集包含133590条特征向量（feature vector），每条向量含42个特征，用于建模5名用户与移动设备的交互行为。每条向量整合了陀螺仪（gyroscope）与加速度计（Accelerometer）的传感器数据。特征含义的详细说明可参见自述文件。
数据集4（162.4 MB）：该数据集包含145465条特征向量（feature vector），每条向量含241个特征，用于建模5名用户同时使用个人计算机与移动设备的交互行为。每条向量整合了两类设备中最具代表性的特征数据。特征含义的详细说明可参见自述文件。
数据集5（878.7 KB）：该数据集由7个子数据集组成。每个子数据集基于不同时长的时间窗口（1小时至24小时），对个人计算机与移动设备的活跃/非活跃区间生成特征向量并进行整合。各时间窗口对应的向量数量如下：1小时：4074条；2小时：2149条；3小时：1470条；4小时：1133条；6小时：770条；12小时：440条；24小时：229条。