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

detects nonreal images

biblio

Visible to the public OC-FakeDect: Classifying Deepfakes Using One-class Variational Autoencoder

Submitted by grigby1 on Fri, 01/15/2021 - 12:02pm
  • detecting Deepfakes
  • Face
  • DeepFake
  • binary-classification based detection
  • binary-classification based methods
  • class-based approach
  • computer-generated image
  • data scarcity limitations
  • deepfakes data
  • deepfakes detection
  • deepfakes generation methods
  • Image reconstruction
  • detection performance
  • detects nonreal images
  • fake face images
  • image forgery method
  • OC-FakeDect
  • one-class anomaly detection problem
  • one-class variational autoencoder
  • person
  • sufficient fake images data
  • Support vector machines
  • Training
  • Anomaly Detection
  • pubcrawl
  • Human behavior
  • Human Factors
  • Metrics
  • Resiliency
  • data privacy
  • Scalability
  • privacy issues
  • learning (artificial intelligence)
  • Streaming media
  • Benchmark testing
  • resilience
  • Forensics
  • face recognition
  • feature extraction
  • image classification
  • pattern clustering
  • object detection

Terms of Use  |  ©2023. CPS-VO