Web: http://arxiv.org/abs/2211.10933

Nov. 22, 2022, 2:20 a.m. | Wenli Sun, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao

cs.CR updates on arXiv.org arxiv.org

In recent years, person Re-identification (ReID) has rapidly progressed with
wide real-world applications, but also poses significant risks of adversarial
attacks. In this paper, we focus on the backdoor attack on deep ReID models.
Existing backdoor attack methods follow an all-to-one/all attack scenario,
where all the target classes in the test set have already been seen in the
training set. However, ReID is a much more complex fine-grained open-set
recognition problem, where the identities in the test set are not …

attack backdoor dynamic identification

Cyber Transformation Consultant - Energy & Utilities

@ PA Consulting | London, United Kingdom

Security Operations Lead

@ Vattenfall | Amsterdam, Netherlands

Technology - Energy and Natural Resources sector, Security Strategy & Governance, Cyber Defence, Identity & Access

@ KPMG Australia | Sydney, Australia

DevSecOps Manager

@ Nexient | United States

IT Security Manager (REF194D)

@ Deutsche Telekom IT Solutions | Budapest, Debrecen, Pécs, Szeged, Hungary

Security GRC Consultant

@ Devoteam | Zaventem, Belgium

Information Security & Data Privacy Specialist

@ SirionLabs | Gurugram, Haryana, India

Junior Security Engineer

@ Eurofins | Barcelona, Spain

Senior Application Security Engineer [Remote - UK]

@ Confluent, Inc. | Remote, England

Threat Analysis Security Engineer

@ MANGOPAY | Paris, France

Sr. Professional Services Consultant II

@ Palo Alto Networks | Denver, CO, United States

Senior Offensive Security Engineer

@ MANGOPAY | Paris, France