africa-dark-web-data-trading
收藏资源简介:
本数据集是一个合成数据集,旨在模拟在暗网市场和地下论坛中交易的非洲相关数据。它属于“非洲网络威胁情报”系列的一部分,专门用于研究非洲地区的数据泄露和非法数据交易模式。数据集包含10,000条平衡记录(正负样本各50%),所有记录均为基于现实世界研究数据生成的合成数据。数据集内容涵盖了多种在暗网上交易的非洲数据,包括银行凭证、信用卡全信息、各国国民身份系统记录(如南非ID号、尼日利亚NIN/BVN、肯尼亚Huduma Namba、加纳GhanaCard等)、移动货币账户数据(如M-Pesa)、电子邮件密码组合、企业数据库转储、政府数据库泄露、生物特征数据、健康记录、电信用户数据等。数据特征非常丰富,包含43个字段,详细描述了每条数据列表的属性,例如数据来源国家、数据类型、出现的暗网市场、泄露源所属部门、威胁行为者类型、支付方式、记录数量、价格、数据新鲜度、是否包含个人身份信息、财务数据、生物特征数据、国民ID数据、移动货币数据等敏感信息标志。此外,还包含卖方信息(如声誉评分、交易次数)、数据已知的滥用用途(如欺诈、身份盗窃、账户接管、SIM交换、贷款欺诈),以及执法和响应情况(如列表是否被撤下、执法部门是否介入、受害者是否被告知)。数据集还包含一系列从原始特征中提取的复合特征,用于表示数据规模、定价情报、新鲜度、敏感性、非洲特异性、卖方画像、下游利用风险和执法差距等维度。该数据集适用于表格分类任务(如区分暗网交易与合法数据列表),也可用于网络安全、威胁情报分析、数据泄露研究、非洲区域网络安全风险评估以及机器学习模型在合成数据上的训练和验证。
This dataset is a synthetic dataset designed to simulate Africa-related data traded on dark web markets and underground forums. It is part of the Africa Cyber Threat Intelligence series, specifically for studying data breaches and illegal data trading patterns in the African region. The dataset contains 10,000 balanced records (50% positive and 50% negative samples), all of which are synthetic data generated based on real-world research data. The dataset covers various types of Africa-related data traded on the dark web, including bank credentials, full credit card information, national identity system records (e.g., South African ID numbers, Nigerian NIN/BVN, Kenyan Huduma Namba, Ghana Card, etc.), mobile money account data (e.g., M-Pesa), email-password combinations, corporate database dumps, government database leaks, biometric data, health records, and telecom subscriber data. The data features are very rich, containing 43 fields that detail the attributes of each data listing, such as source country, data type, dark web market involved, sector of the breach source, threat actor type, payment method, record count, price, data freshness, and flags for sensitive information like personally identifiable information, financial data, biometric data, national ID data, and mobile money data. Additionally, it includes seller information (e.g., reputation score, number of transactions), known misuse purposes of the data (e.g., fraud, identity theft, account takeover, SIM swapping, loan fraud), and law enforcement and response details (e.g., whether the listing was taken down, law enforcement involvement, victim notification). The dataset also includes a series of composite features extracted from the original features to represent dimensions such as data scale, pricing intelligence, freshness, sensitivity, Africa-specificity, seller profiling, downstream exploitation risk, and law enforcement gaps. This dataset is suitable for tabular classification tasks (e.g., distinguishing dark web transactions from legitimate data listings) and can be used for cybersecurity, threat intelligence analysis, data breach research, cybersecurity risk assessment in the African region, and training and validation of machine learning models on synthetic data.




