all InfoSec news
Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models. (arXiv:2206.14477v2 [cs.LG] UPDATED)
July 5, 2022, 1:20 a.m. | Lele Wang, Bin Liu
cs.CR updates on arXiv.org arxiv.org
Training an ensemble of different sub-models has empirically proven to be an
effective strategy to improve deep neural networks' adversarial robustness.
Current ensemble training methods for image recognition usually encode the
image labels by one-hot vectors, which neglect dependency relationships between
the labels. Here we propose a novel adversarial ensemble training approach to
jointly learn the label dependencies and the member models. Our approach
adaptively exploits the learned label dependencies to promote the diversity of
the member models. We test …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Security Compliance Architect - Experian Health (Can be REMOTE from anywhere in the US)
@ Experian | ., ., United States
IT Security Specialist
@ Ørsted | Kuala Lumpur, MY
Senior, Cyber Security Analyst
@ Peloton | New York City
Cyber Security Engineer | Perimeter | Firewall
@ Garmin Cluj | Cluj-Napoca, Cluj County, Romania
Pentester / Ethical Hacker Web/API - Vast/Freelance
@ Resillion | Brussels, Belgium