arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.05906cs.CRcs.CVcs.LG
收藏

用于恶意软件图像分类的深度多任务学习

Deep Multi-Task Learning for Malware Image Classification

University of Colorado Colorado Springs(科罗拉多大学科罗拉多斯普林斯分校)

Ahmed Bensaoud, Jugal Kalita

AI总结:

本文提出深度多任务学习框架,将恶意软件特征转为BMP/PNG图像分类,在约10万样本的七任务中用PReLU取得99.87%以上准确率,并可识别多种混淆手段。

摘要:

恶意软件是一个有害的全球性问题。本文提出一种新颖的多任务学习框架,用于恶意软件图像分类,以实现准确、快速的恶意软件检测。我们从恶意软件特征生成位图(BMP)和PNG图像,并将其输入深度学习分类器。我们这一先进的多任务学习方法已在一个新数据集上接受测试;为此,我们收集了约100,000个良性和恶意的PE、APK、Mach-o及ELF样本。针对七个任务的实验分别使用ReLU、LeakyReLU、PReLU和ELU四种激活函数进行测试,结果表明PReLU在所有任务上均取得超过99.87%的最高准确率。除了在准确率方面达到先进方法水平外,我们的模型还能有效检测加壳、加密和指令重叠等多种混淆方法,从而进一步强化了对模型有效性的论证。

英文摘要:

Malicious software is a pernicious global problem. A novel multi-task learning framework is proposed in this paper for malware image classification for accurate and fast malware detection. We generate bitmap (BMP) and (PNG) images from malware features, which we feed to a deep learning classifier. Our state-of-the-art multi-task learning approach has been tested on a new dataset, for which we have collected approximately 100,000 benign and malicious PE, APK, Mach-o, and ELF examples. Experiments with seven tasks tested with 4 activation functions, ReLU, LeakyReLU, PReLU, and ELU separately demonstrate that PReLU gives the highest accuracy of more than 99.87% on all tasks. Our model can effectively detect a variety of obfuscation methods like packing, encryption, and instruction overlapping, strengthing the beneficial claims of our model, in addition to achieving the state-of-art methods in terms of accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑