U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Just Science Podcast: Just Deep Fakes

NCJ Number
255147
Author(s)
Catalin Grigoras; Cole Whitecotton
Date Published
August 2020
Length
3 pages
Annotation

This seventh episode in the National Institute of Justice's (NIJ's) Just Science podcast series is an interview with Dr. Catalin Grigoras and Cole Whitecotton from the National Center for Media Forensics, who discuss "deepfakes," defined in interview background material as "a form of synthetic media that replaces an existing image with someone else's likeness."

Abstract

In their work, both Grigoras and Whitecotton have focused on understanding how deepfakes are created and how they can be detected. In the interview, they discuss the capability, implications, and the future of deepfake technology. Background information for the interview notes that deepfake technology has become more sophisticated in the last few years, such that the synthetic image is nearly indiscernible from the person being imitated. This creates problems for forensic analysis. The interview covers the use of artificial intelligence to create deepfakes for both photo and video images. In forensic contexts, deepfakes may be involved in the commission of a crime or the use of deepfakes that lead to false conclusions about an event or a person that corrupts decisionmaking and manipulates outcomes. It is crucial in forensic science to be able to expose such deep fakes. The interview focuses on these efforts.