Web: http://arxiv.org/abs/2211.10908

Nov. 22, 2022, 2:20 a.m. | Jiaqi Xue, Qian Lou

cs.CR updates on arXiv.org arxiv.org

Emerging self-supervised learning (SSL) has become a popular image
representation encoding method to obviate the reliance on labeled data and
learn rich representations from large-scale, ubiquitous unlabelled data. Then
one can train a downstream classifier on top of the pre-trained SSL image
encoder with few or no labeled downstream data. Although extensive works show
that SSL has achieved remarkable and competitive performance on different
downstream tasks, its security concerns, e.g, Trojan attacks in SSL encoders,
are still not well-studied. In …

attacks one target trojan

Senior Cloud Security Engineer

@ HelloFresh | Berlin, Germany

Senior Security Engineer

@ Reverb | Remote, US

I.S. Security Analyst

@ YVFWC | Yakima, WA

Snr Professional Services Consultant - XSIAM

@ Palo Alto Networks | Madrid, Spain

Data Governor and Security Specialist

@ Dynatrace | Milan, Italy

Principal Windows Exploit Security Researcher (Cortex XDR)

@ Palo Alto Networks | Tel Aviv-Yafo, Israel

Information System Security Officer (ISSO)

@ SciTec | Boulder, Colorado, United States

Application Security Design Architect

@ Fivesky | Alpharetta, GA

Product Cybersecurity Lead

@ SciTec | Boulder, Colorado, United States

Cybersecurity Consultant

@ Sia Partners | Rotterdam, Netherlands

Senior Cybersecurity Engineer

@ Visa | Austin, TX, United States

Manager Pentest H/F

@ Hifield | Sèvres, France