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

OOD queries

biblio

Visible to the public Defending Against Model Stealing Attacks With Adaptive Misinformation

Submitted by grigby1 on Thu, 01/28/2021 - 1:12pm
  • Metrics
  • training dataset
  • security of data
  • security
  • Scalability
  • Resiliency
  • resilience
  • query processing
  • pubcrawl
  • Predictive models
  • Perturbation methods
  • out-of-distribution inputs
  • OOD queries
  • neural nets
  • model stealing attacks
  • Adaptation models
  • learning (artificial intelligence)
  • labeled dataset
  • Human behavior
  • deep neural networks
  • Data models
  • Computational modeling
  • Cloning
  • clone model
  • black-box query access
  • attacker clone model
  • attacker
  • Adversary Models
  • Adaptive Misinformation

Terms of Use  |  ©2023. CPS-VO