AI RESEARCH
Contrastive Learning and Correlation Clustering for Sequences of Network Telescope Data
arXiv CS.LG
•
ArXi:2606.04733v1 Announce Type: new 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 pre