arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.11076cs.CRcs.CL
收藏

用于专业网络威胁情报的多级微调、数据增强和少样本学习

Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence

Technical University of Darmstadt(达姆施塔特工业大学)

Markus Bayer, Tobias Frey, Christian Reuter

摘要:

随着系统变得越来越大、越来越复杂,从开源收集网络威胁情报对于维护和实现高水平的安全性变得越来越重要。然而,这些公开来源往往受到信息过载的影响。因此,应用机器学习模型将信息量压缩到必要的程度是有用的。然而,先前的研究和应用表明,现有的分类器由于泛化能力低而无法提取有关新兴网络安全事件的特定信息。因此,我们提出了一个系统来克服这个问题,训练一个新的分类器为每个新的事件。由于这需要大量的标记数据使用标准的训练方法,我们结合了三种不同的低数据制度的技术-迁移学习,数据增强,和少样本学习-训练一个高质量的分类器从很少的标记实例。我们使用来自2021年Microsoft Exchange Server数据泄露的新数据集评估了我们的方法,该数据集由三位专家标记。我们的研究结果显示,与标准训练方法相比,F1分数增加了21分以上,与少样本学习中最先进的方法相比,F1分数增加了18分以上。此外,使用该方法和32个实例训练的分类器仅比使用1800个实例训练的分类器差不到5个F1得分点。

英文摘要:

Gathering cyber threat intelligence from open sources is becoming increasingly important for maintaining and achieving a high level of security as systems become larger and more complex. However, these open sources are often subject to information overload. It is therefore useful to apply machine learning models that condense the amount of information to what is necessary. Yet, previous studies and applications have shown that existing classifiers are not able to extract specific information about emerging cybersecurity events due to their low generalization ability. Therefore, we propose a system to overcome this problem by training a new classifier for each new incident. Since this requires a lot of labelled data using standard training methods, we combine three different low-data regime techniques - transfer learning, data augmentation, and few-shot learning - to train a high-quality classifier from very few labelled instances. We evaluated our approach using a novel dataset derived from the Microsoft Exchange Server data breach of 2021 which was labelled by three experts. Our findings reveal an increase in F1 score of more than 21 points compared to standard training methods and more than 18 points compared to a state-of-the-art method in few-shot learning. Furthermore, the classifier trained with this method and 32 instances is only less than 5 F1 score points worse than a classifier trained with 1800 instances.

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。

↑