dtrizna/quovadis-ember

该数据集包含了93533个32位可移植可执行文件(PE)的EMBER特征，这些特征用于支持两篇研究论文：Quo Vadis:混合机器学习元模型基于上下文和行为恶意软件表征和Nebula：用于动态恶意软件分析的自注意力机制。数据集分为训练集和测试集，分别收集于2022年1月和4月，以研究恶意软件的概念漂移现象。数据集中的文件被标记为良性或分为七个不同的恶意软件家族。

This dataset contains EMBER features from 93533 32-bit portable executables (PE) used in support of two research papers: Quo Vadis: Hybrid Machine Learning Meta-Model Based on Contextual and Behavioral Malware Representations and Nebula: Self-Attention for Dynamic Malware Analysis. The dataset is divided into a training set and a test set, collected in January and April 2022, respectively, to study the concept drift phenomenon in malware. Files in the dataset are labeled as benign or belong to one of seven different malware families.