Skip to main navigation
Skip to search
Skip to main content
Rutgers, The State University of New Jersey Home
Help & FAQ
Home
Profiles
Research units
Core Facilities
Federal Grants
Research output
Search by expertise, name or affiliation
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
Zhun Deng
,
Linjun Zhang
, Amirata Ghorbani
, James Zou
Research output
:
Contribution to journal
›
Conference article
›
peer-review
15
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Improving Adversarial Robustness via Unlabeled Out-of-Domain Data'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Adversarial Robustness
100%
Unlabeled Data
100%
Out-of-domain Data
100%
Structural Information
33%
Multiple Domains
33%
Object Recognition
33%
Sparsity
33%
Adversarial Attack
33%
Model Robustness
33%
Labeled Data
33%
Robust Classification
33%
Sample Complexity
33%
Data Augmentation
33%
Unlabeled Samples
33%
Distribution Class
33%
Recognition Dataset
33%
CIFAR-10
33%
Out-of-domain
33%
Limited Labeled Data
33%
Computer Science
Data Domain
100%
Unlabeled Data
100%
Object Recognition
33%
Sparsity
33%
Adversarial Machine Learning
33%
Multiple Domain
33%
Data Augmentation
33%
Limited Labeled Data
33%
Unlabeled Sample
33%