SDN DDOS ATTACK IMAGE DATASET

It is now widely known fact that the Cloud computing and Software defined network paradigms have received a wide acceptance from researchers, academia and the industry. But the wider acceptance of cloud computing and SDN paradigms are hampered by increasing security threats. One of the several facts is that the advancements in processing facilities currently available are implicitly helping the attackers to attack in various directions. For example, it is visible that the conventional DoS attacks are now extended to cloud environments as DDoS attacks. With a huge number of security threats that are continuously occurring in computer networks and environments such as software defined networks (SDN) and Cloud computing, there is a demand to address security solutions that have a better reliability when compared to existing security solutions that are designed by considering datasets that did not meet the assessment and evaluation criterion which must be considered during the design of IDS systems. In [2], Nisha Ahuja, Gaurav Singal, and Debajyoti Mukhopadhyay have generated DDoS attack dataset for Software Defined Networks. This dataset was generated using mininet emulator. The dataset is available in the form of csv file(.csv) . The original version of dataset consists of 104345 traffic instances defined over 23 features.For evaluating performance of ML and DL based Intrusion Detection System, we have converted the DDOS attack SDN Dataset [3] in csv format to SDN DDoS attack image dataset consisting of network traffic image instances. Each traffic image instance in SDN DDoS attack image dataset is of 5x5 pixel size.

众所周知，云计算与软件定义网络（Software Defined Network, SDN）范式已获得研究者、学术界与工业界的广泛认可。但云计算与SDN范式的进一步推广却因日益严峻的安全威胁受到阻碍。其中一项核心诱因在于，当前各类处理设施的技术进步实则暗中为攻击者提供了多维度的攻击便利。例如，传统拒绝服务（Denial of Service, DoS）攻击现已演进为针对云环境的分布式拒绝服务（Distributed Denial of Service, DDoS）攻击。鉴于计算机网络及软件定义网络、云计算等场景中持续涌现大量安全威胁，现有入侵检测系统（Intrusion Detection System, IDS）在设计阶段所依托的数据集未满足评估准则，导致对应的安全解决方案可靠性欠佳，因此亟需研发可靠性更优的安全解决方案。文献[2]中，Nisha Ahuja、Gaurav Singal与Debajyoti Mukhopadhyay针对软件定义网络构建了DDoS攻击数据集。该数据集基于Mininet模拟器生成，以逗号分隔值（CSV）格式存储，原始版本包含104345条流量实例，涵盖23项特征。为评估基于机器学习（Machine Learning, ML）与深度学习（Deep Learning, DL）的入侵检测系统性能，我们将文献[3]中的CSV格式SDN DDoS攻击数据集转换为包含网络流量图像实例的SDN DDoS攻击图像数据集。该数据集中的每条流量图像实例均为5×5像素尺寸。

搜集汇总

背景与挑战

背景概述

该数据集是一个专门用于评估机器学习和深度学习入侵检测系统性能的图像数据集，针对软件定义网络（SDN）中的DDoS攻击安全威胁而构建。它由公开的CSV格式DDoS攻击SDN数据集转换而来，包含网络流量图像实例，每个图像大小为5x5像素，适用于IoT、机器学习和云计算领域的研究。