加密应用识别与公害行为发现流量数据集

本数据集聚焦于加密应用识别与网络公害行为发现，通过自动化工具在真实网络环境下采集流量数据，涵盖TLS1.3协议移动应用、常见加密应用、网络公害行为及VPN类工具、APT C&C隐蔽通道、IM工具等加密流量。数据采集时间截至2024年10月，采用flowcontainer工具提取流级别信息，并以json文件形式保存。数据集包含547种TLS1.3协议移动应用、349种常见加密应用、5种网络公害行为及300种VPN类工具等加密流量样本，覆盖广泛的应用类型与行为场景。数据质量控制通过自动化采集与标准化处理实现，确保数据的准确性与一致性。本数据集为加密应用识别、网络公害行为检测及相关技术研究提供了重要的实验基础与数据支持，具有显著的科研与应用价值。

This dataset is dedicated to encrypted application identification and detection of network harmful behaviors. Traffic data was collected in real-world network environments via automated tools, encompassing encrypted traffic from TLS 1.3 protocol mobile applications, common encrypted applications, network harmful behaviors, VPN tools, APT Command and Control (C&C) covert channels, instant messaging (IM) tools, and other related categories. The data collection process concluded in October 2024. Flow-level information was extracted using the FlowContainer tool, with all data stored in JSON format files. The dataset comprises encrypted traffic samples from 547 TLS 1.3 protocol mobile applications, 349 common encrypted applications, 5 categories of network harmful behaviors, 300 VPN tools, and other relevant types, covering a wide spectrum of application categories and behavioral scenarios. Data quality control is achieved through automated collection and standardized processing, guaranteeing the accuracy and consistency of the dataset. This dataset offers critical experimental foundations and data support for research on encrypted application identification, network harmful behavior detection, and related technical studies, boasting substantial scientific research and practical application value.

搜集汇总

背景与挑战

背景概述

该数据集是一个用于加密应用识别与网络公害行为发现的流量数据集，采集自真实网络环境，涵盖TLS1.3协议移动应用、常见加密应用、网络公害行为及VPN类工具等多种加密流量样本，数据量约875.69MB。它通过自动化工具提取流级别信息并以json格式保存，为相关技术研究提供了重要的实验数据支持。