介绍：
电子邮箱是网络中最常见的通信工具之一，其安全一直受到广泛的关注。针对邮箱账户的探测攻击作为许多传统攻击手段以及部分APT攻击一部分，对邮箱账户的安全有着巨大的挑战，现有的研究缺乏对此类分布式邮箱探测数据的研究和分析。因此，我们在某网络出口采集了邮箱探测攻击流量，并形成了邮箱探测数据集（CNEPD），该数据集包括2018年内的邮箱探测记录，总共764,537条记录，包括了3,292,831次攻击。每一条记录包括探测网段（segment）,探测ip地址(ip),被探测邮箱账号（username）,探测日期（date）,探测次数（count）共五个字段。为了脱除敏感信息，将网段、IP、邮箱账号进行随机标号处理,将日期转化为数字。CNEPD数据集在一定程度上能够为该类攻击的研究和防御提供参考和数据支持。
格式说明：
本数据集为csv格式文件，以“;”为分隔符，每一行表示一条记录，如下：
1;1271;30695;1004615;3;7
分别为序号、网段编号、IP地址编号、邮箱用户名编号、探测日期、探测次数。
注意：
1.数据使用方有义务将使用数据获得的成果(项目、论文等)主动告知四川大学网络空间安全研究院；在利用该数据集进行深入研究而获得的成果中，应指明数据的提供方（四川大学网络空间安全研究院）。
2.本数据集仅用于学术研究，禁止商用。
Introduction:
E-mail has become a common social tool onthe internet and its security has been a hot-spot. Attackers prefer to useE-mail to pass on malware or phishing so that they can carry out differentkinds of attacks such as some traditional network attacks or the APTpenetration attack. There is a lack of research and dataset about e-mailprobing attack. In this project, we construct and release a new dataset calledCampus Network E-mail Probing Dataset (CNEPD), containing 764,537 records and3,292,831 attacks. Each record in CNEPD consists of attack date (Date), IP address(IP), class C network segment (Segment), username of e-mail account (Username)and the number of probing (count). For the purpose of clearing the sensitiveinformation, we anonymize the data set, randomly numbering the date, IPaddress, network segment and username of each record. We believe that therelease of CNEPD can provide reference and data support for the research anddefense of such attacks.
FormatDescription:
This data set is a CSV file, with";" as the separator. Each line represents a record, as follows:
1;1271;30695;1004615;3;7
They represent ID of a record, ID of network segment, ID of IPaddress, ID of e-mail username, probing date and probing times.
Attention:
1. Dataset users shall voluntarily informCyberspace Security Research Institute of Sichuan University of the resultsobtained from the data, such as projects, papers, etc. The provider of the dataset,Cyberspace Security Research Institute of Sichuan University, should beidentified in the results of in-depth research using the dataset.
2. This data set is only used for academic research and commercialuse is prohibited.
