Skip to Main Content Area
CPS-VO
Contact Support
Browse
Calendar
Announcements
Repositories
Groups
Search
Search for Content
Search for a Group
Search for People
Search for a Project
Tagcloud
› Go to login screen
Not a member?
Click here to register!
Forgot username or password?
Cyber-Physical Systems Virtual Organization
Read-only archive of site from September 29, 2023.
CPS-VO
TensorClog poisoning technique
biblio
TensorClog: An Imperceptible Poisoning Attack on Deep Neural Network Applications
Submitted by grigby1 on Wed, 11/04/2020 - 2:12pm
resilience
neural nets
Neural networks
Perturbation methods
poisoning attack
privacy
privacy protection purpose
pubcrawl
real-world application
lower inference accuracy
Resiliency
Scalability
security of data
TensorClog poisoning technique
test error
Training
user data
user privacy violations
deep neural network applications
adversarial attack
AI Poisoning
CIFAR-10 dataset results
converged training loss
data converges
data privacy
data results
deep learning
abusive data collection
deep neural networks
different limited information attack scenarios
feature extraction
Human behavior
imperceptible poisoning attack
internet
Internet application providers
learning (artificial intelligence)
