Since 2017, deepfakes have emerged across the internet. Deepfakes are audio clips, video clips, or still images that are intentionally constructed to deceive an audience into believing something that may not be true. This recent technological exploitation has brought with it a host of practical and ethical concerns. In 2020, corporations and scholars alike have come to realize that deepfakes are a critical issue that must be addressed. With so many facets of society wallowing in profound divisiveness, deepfakes are one more way to amplify and extend this unhealthy discord. This thesis examines the risk associated with deepfakes and whether this growing menace can be reduced or eliminated through a deepfake detection system. First, a common analytical framework for a deepfake detection system is presented. This framework creates a baseline set of components, including two new pieces yet to be considered. Second, a multisource case study methodology is used that evaluates multiple existing deepfake detection systems to examine how each fit within the architecture of the framework. Third, an analysis of the strengths and weaknesses of each system is performed to further provide validation of the research. The creation of a new deepfake detection system architecture can be used to develop new and improved systems to combat the growing danger posed by deepfakes. As the methods used to create deepfakes become more robust, so too must the technology tools used to combat these dangers.
|Commitee:||Bein, Doina, Inventado, Paul|
|School:||California State University, Fullerton|
|School Location:||United States -- California|
|Source:||MAI 82/6(E), Masters Abstracts International|
|Subjects:||Computer science, Journalism, Information Technology, Computer Engineering, Management, Web Studies, Multimedia Communications|
|Keywords:||Deepfakes, Internet, Ethical concerns, Detection systems, System architecture|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be