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
      
 
Not a member?
Click here to register!
Forgot username or password?
 
Home
National Science Foundation

Cyber-Physical Systems Virtual Organization

Read-only archive of site from September 29, 2023.

CPS-VO

poisonous data

biblio

Visible to the public Deep Learning Poison Data Attack Detection

Submitted by grigby1 on Wed, 11/04/2020 - 2:15pm
  • model definitions
  • variational inference approach
  • Variational inference
  • transfer learning
  • training phase
  • testing data
  • system-critical applications
  • Scalability
  • Resiliency
  • resilience
  • pubcrawl
  • pre-trained model parameters
  • poisonous data
  • poisoned training data
  • neural nets
  • network attack
  • adversarial information
  • MNIST data
  • maximum entropy principle
  • Maximum Entropy method
  • learning (artificial intelligence)
  • Human behavior
  • Entropy
  • deep neural networks
  • deep learning poison data attack detection
  • deep learning
  • computer network security
  • CNN model
  • Bayesian statistic
  • attacking training data
  • AI Poisoning

Terms of Use  |  ©2023. CPS-VO