all InfoSec news
Towards Understanding Dual BN In Hybrid Adversarial Training
March 29, 2024, 4:11 a.m. | Chenshuang Zhang, Chaoning Zhang, Kang Zhang, Axi Niu, Junmo Kim, In So Kweon
cs.CR updates on arXiv.org arxiv.org
Abstract: There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples (termed Hybrid-AT). With the assumption that adversarial and clean samples are from two different domains, a common practice in prior works is to adopt Dual BN, where BN and BN are used for adversarial and clean branches, respectively. A popular belief for motivating Dual BN is that estimating …
adversarial arxiv batch cs.ai cs.cr cs.cv cs.lg domains hybrid normalization practice training understanding
More from arxiv.org / cs.CR updates on arXiv.org
IDEA: Invariant Defense for Graph Adversarial Robustness
1 day, 2 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
1 day, 2 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Senior InfoSec Manager - Risk and Compliance
@ Federal Reserve System | Remote - Virginia
Security Analyst
@ Fortra | Mexico
Incident Responder
@ Babcock | Chester, GB, CH1 6ER
Vulnerability, Access & Inclusion Lead
@ Monzo | Cardiff, London or Remote (UK)
Information Security Analyst
@ Unissant | MD, USA