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

fraudulent social media profiles

biblio

Visible to the public Evading Deepfake-Image Detectors with White- and Black-Box Attacks

Submitted by grigby1 on Thu, 03/04/2021 - 2:35pm
  • security of data
  • neural nets
  • neural network
  • optimization
  • Perturbation methods
  • popular forensic approach
  • pubcrawl
  • resilience
  • Resiliency
  • Robustness
  • Metrics
  • significant vulnerabilities
  • social networking (online)
  • state- of-the-art classifier
  • synthesizer
  • synthetic content
  • synthetically-generated content
  • target classifier
  • Training
  • Twitter
  • fraudulent social media profiles
  • white box
  • security
  • attack case studies
  • AUC
  • black-box attack
  • composability
  • deepfake-image detectors
  • disinformation campaigns
  • Forensics
  • White Box Security
  • Generators
  • image area
  • image classification
  • Image forensics
  • image generators
  • image representation
  • image sensors
  • image-forensic classifiers
  • learning (artificial intelligence)

Terms of Use  |  ©2023. CPS-VO