Op2Vec

Op2Vec数据集是由工程与技术大学计算机科学系的研究团队开发的，用于端到端检测Android恶意软件。该数据集包含28,570个Android应用程序，旨在通过自动学习操作码（opcodes）嵌入来避免手动特征工程的需求。数据集的内容包括从Android源代码中提取的操作码序列，通过Op2Vec技术转换为向量表示。创建过程中，研究团队收集了来自不同市场的应用程序，提取了Dalvik可执行文件（.dex）并进一步提取了操作码序列。该数据集的应用领域主要集中在通过深度学习模型自动检测和分类Android恶意软件，以解决现有技术中依赖专家知识和手动特征提取的问题。

The Op2Vec dataset was developed by a research team from the Department of Computer Science, University of Engineering and Technology, for end-to-end detection of Android malware. This dataset comprises 28,570 Android applications, designed to eliminate the need for manual feature engineering through automated learning of opcode embeddings. The dataset contains opcode sequences extracted from Android application source code, which are converted into vector representations using the Op2Vec technique. During the dataset's development, the research team collected applications from various markets, extracted Dalvik Executable (.dex) files, and further derived the corresponding opcode sequences. The primary application scope of this dataset is focused on the automatic detection and classification of Android malware via deep learning models, to address the drawbacks of existing technologies that rely on expert knowledge and manual feature extraction.