A Statistical Framework for Deepfake Detection

reportActive / Technical Report | Accesssion Number: AD1178519 | Open PDF

Abstract:

Deepfakes are believable media generated by neural networks(Mirsky and Lee 2021)Potential Dangers: Impersonation of political figures and celebrities. Defamation of citizens Extension of catfishing. >100k hours of video uploaded to web everyday!

Author(s):
Gallagher, Shannon ; Ross, Dominic ; Mellon, Jeffrey ; Bernaciak, Catherine
Author Organization(s):
CARNEGIE-MELLON UNIV PITTSBURGH PA
Funding Organization(s):
AIR FORCE LIFE CYCLE MANAGEMENT CENTER HANSCOM AFB MA, HANSCOM AFB , MA
Document Type:
Technical Report/Briefing Charts
Publication Date:
2022 Aug 01
Pagination:
7

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution Code:
A - Approved For Public Release
Distribution Statement: Public Release

RECORD

Collection: TRECMS
Identifying Numbers
Contract Number(s):
FA8702-15-D-0002
Subject Terms
Communities of Interest:
No COI(s) Identified
Descriptor(s):
software development, detection, deepfakes, detectors, engineering, materials, neural networks, universities, data sets, data storage systems, department of defense, guarantees, governments, video
Subject Categories:
Mathematical and Computer Sciences
Creation Date:
2022 Aug 29
Update Date:
2022 Nov 02