论文标题
安全数据的基于注意力的自我监督功能学习
Attention-Based Self-Supervised Feature Learning for Security Data
论文作者
论文摘要
尽管机器学习在网络安全中的应用迅速增长，但大多数模型都使用手动构造的功能。这种手动方法容易出错，需要域专业知识。在本文中，我们设计了一个自我监督的序列到序列模型，并注意以学习在网络安全应用程序中通常使用的数据的嵌入。该方法在两个现实世界公共数据集上进行了验证。学习的功能用于异常检测模型，并从基线方法中使用的功能更好。
While applications of machine learning in cyber-security have grown rapidly, most models use manually constructed features. This manual approach is error-prone and requires domain expertise. In this paper, we design a self-supervised sequence-to-sequence model with attention to learn an embedding for data routinely used in cyber-security applications. The method is validated on two real world public data sets. The learned features are used in an anomaly detection model and perform better than learned features from baseline methods.
