基于注意力的安全数据自监督特征学习
Attention-Based Self-Supervised Feature Learning for Security Data
摘要:
虽然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建的特征。这种手动方法容易出错,需要领域专业知识。在本文中,我们设计了一个自我监督的序列到序列模型,并注意学习网络安全应用中经常使用的数据的嵌入。该方法在两个真实世界的公共数据集上进行了验证。学习的特征用于异常检测模型中,并且比来自基线方法的学习特征表现得更好。
英文摘要:
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.
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。