arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.04733cs.LGcs.NI
收藏

对比学习与相关聚类在网络望远镜数据序列中的应用

Contrastive Learning and Correlation Clustering for Sequences of Network Telescope Data

TU Dresden(德累斯顿技术大学);HAW Hamburg(汉堡应用技术大学);Center for Scalable Data Analytics and AI Dresden/Leipzig(德累斯顿/莱比锡可扩展数据与人工智能研究中心)

Jannik Presberger, Alexander Männel, Maynard Koch, Thomas C. Schmidt, Matthias Wählisch, Bjoern Andres

AI总结:

本文提出一种无需预训练和标注的对比学习变压器模型,用于估计网络流记录序列间的语义关系,并通过相关聚类实现扫描器行为的无监督分组。

摘要:

理解互联网扫描器的活动具有挑战性;通常需要识别源之间的关系,而这一任务的语义标注非常稀缺。本文研究是否可以通过对比学习,无需预训练和标注,来估计网络流记录序列之间具有语义意义的成对关系。为此,我们提出一个变压器模型,嵌入经过最小预处理的网络流记录序列,并使用对比学习进行训练。利用该模型获得的相似度,我们定义了一个相关聚类问题并局部求解。实验表明:来自同一源的序列之间的学习相似度平均高于来自不同源的序列,并且这一特性可推广到未见过的源和未见过的序列。此外,相关聚类产生的聚类结果与扫描器标签一致。算法和重现实验的完整源代码已公开。

英文摘要:

Understanding activities of Internet scanners is challenging; it often requires identifying relationships between sources, a task for which semantic annotations are scarce. This work investigates whether semantically meaningful pairwise relationships between sequences of network flow records can be estimated by contrastive learning, without pretraining and without annotations. To this end, we propose a transformer model that embeds minimally preprocessed sequences of network flow records and train it using contrastive learning. With the similarities obtained from this model, we state a correlation clustering problem and solve it locally. Experimentally, we show: Learned similarities are higher on average for sequences originating from the same source than for sequences originating from different sources, and this property generalizes to unseen sequences of unseen sources. Moreover, correlation clustering yields clusters consistent with scanner labels. The complete source code of the algorithms and for reproducing the experiments is publicly available.

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。

↑