MalVis
收藏资源简介:
MalVis是一个大规模的基于图像的Android恶意软件分类框架和数据集,由特拉华大学电气与计算机工程系的研究人员开发。该数据集包含超过130万张图像,分为九种恶意软件类别和一个良性类别。数据集着重于解决现有可视化方法中特征表示不足、可解释性有限、数据集规模小和数据访问受限等问题,通过集成熵和N-gram分析,强调恶意软件字节码中的有意义结构和异常操作模式。MalVis数据集为研究人员和实际安全应用提供了宝贵的资源,有助于提高恶意软件检测和分类的准确性和可解释性。
MalVis is a large-scale image-based Android malware classification framework and dataset, developed by researchers from the Department of Electrical and Computer Engineering, University of Delaware. This dataset contains over 1.3 million images, categorized into nine malware classes and one benign class. It focuses on addressing the limitations of existing visualization methods, including insufficient feature representation, limited interpretability, small dataset scale, and restricted data access. By integrating entropy and N-gram analyses, it highlights the meaningful structural and anomalous operational patterns within malware bytecodes. The MalVis dataset serves as a valuable resource for researchers and practical security applications, helping to improve the accuracy and interpretability of malware detection and classification.




