arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2212.02663cs.LGcs.AIcs.CR
收藏

基于度量嵌入的高效恶意软件分析

Efficient Malware Analysis Using Metric Embeddings

Mandiant Inc.(曼迪安特公司);University of Florida(佛罗里达大学);Booz Allen Hamilton(博思艾伦汉密尔顿公司);University of Maryland(马里兰大学)

Ethan M. Rudd, David Krisiloff, Scott Coull, Daniel Olszewski, Edward Raff, James Holt

摘要:

在本文中,我们将探讨使用度量学习将Windows PE文件嵌入到低维向量空间中,以供下游各种应用程序使用,包括恶意软件检测、家族分类和恶意软件属性标记。具体来说,我们使用计算成本高昂、基于反汇编的恶意功能来丰富恶意和良性PE文件的标签。使用这些功能,我们得到几种不同类型的度量嵌入,利用嵌入神经网络通过对比损失,斯皮尔曼秩相关性,及其组合训练。然后,我们检查了在EMBER和SOREL数据集上执行的各种传输任务的性能,证明了对于几个任务,低维,计算效率高的度量嵌入保持性能几乎没有衰减,这提供了快速重新训练的潜力。最后,我们检查的实际考虑使用我们提出的嵌入方法,如对抗性规避的鲁棒性和引入特定于任务的辅助目标,以提高关键任务的性能。

英文摘要:

In this paper, we explore the use of metric learning to embed Windows PE files in a low-dimensional vector space for downstream use in a variety of applications, including malware detection, family classification, and malware attribute tagging. Specifically, we enrich labeling on malicious and benign PE files using computationally expensive, disassembly-based malicious capabilities. Using these capabilities, we derive several different types of metric embeddings utilizing an embedding neural network trained via contrastive loss, Spearman rank correlation, and combinations thereof. We then examine performance on a variety of transfer tasks performed on the EMBER and SOREL datasets, demonstrating that for several tasks, low-dimensional, computationally efficient metric embeddings maintain performance with little decay, which offers the potential to quickly retrain for a variety of transfer tasks at significantly reduced storage overhead. We conclude with an examination of practical considerations for the use of our proposed embedding approach, such as robustness to adversarial evasion and introduction of task-specific auxiliary objectives to improve performance on mission critical tasks.

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。

↑