Feb. 9, 2023, 2:10 a.m. | Korawat Tanwisuth, Shujian Zhang, Pengcheng He, Mingyuan Zhou

cs.CR updates on arXiv.org arxiv.org

Unsupervised clustering under domain shift (UCDS) studies how to transfer the
knowledge from abundant unlabeled data from multiple source domains to learn
the representation of the unlabeled data in a target domain. In this paper, we
introduce Prototype-oriented Clustering with Distillation (PCD) to not only
improve the performance and applicability of existing methods for UCDS, but
also address the concerns on protecting the privacy of both the data and model
of the source domains. PCD first constructs a source clustering …

address clustering data domain domains knowledge learn performance privacy protecting prototype representation studies target under

Enterprise Threat Intel Analyst

@ Resource Management Concepts, Inc. | Quantico, Virginia, United States

IT Security Engineer III

@ Mitsubishi Heavy Industries | Houston, TX, US, 77046

Cyber Intelligence Vice President, Threat Intelligence

@ JPMorgan Chase & Co. | Singapore, Singapore

Assistant Manager, Digital Forensics

@ Interpath Advisory | Manchester, England, United Kingdom

Tier 3 - Forensic Analyst, SME

@ Resource Management Concepts, Inc. | Quantico, Virginia, United States

Incident Response, SME

@ Resource Management Concepts, Inc. | Quantico, Virginia, United States