Can Deepfakes be created on a whim?
Can Deepfakes be created on a whim?
复制标题
DOI：
10.1145/3543873.3587581
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Pulak Mehta;Gauri Jagatap;Kevin Gallagher;Brian Timmerman;Progga Deb;S. Garg;R. Greenstadt;Brendan Dolan-Gavitt
中科院分区：
文献类型：
--
作者：
Pulak Mehta;Gauri Jagatap;Kevin Gallagher;Brian Timmerman;Progga Deb;S. Garg;R. Greenstadt;Brendan Dolan-Gavitt
最近机器学习和计算机视觉的进步导致了Deepfake的激增。随着时间的推移，随着技术的民主化，人们越来越担心新手用户可能会制造Deepfake，以诋毁他人并破坏公共话语。在本文中，我们进行了用户研究，以了解具有高级计算机技能和不同水平的计算机科学专业知识的参与者是否能够使用有限的媒体文件创建一个人说目标陈述的深度假象。我们进行了两项研究；在第一项研究中(n=39)，参与者尝试使用他们想要的任何工具在有限的时间框架内创建一个目标Deepfac。在第二项研究中(n=29)，参与者使用预先指定的基于深度学习的工具来创建相同的Deepfac。我们发现，在第一个研究中，参与者成功地用音频和视频创建了完整的深度伪装，而在第二个用户研究中，参与者中成功地将目标语音与目标视频缝合在一起。我们进一步使用深伪检测软件工具以及基于人类审查员的分析，将成功生成的深伪输出分类为假、可疑或真实。软件检测器将Deepfake归类为假冒视频，而人类审查员将视频归类为假冒视频。我们的结论是，对于新手用户来说，如果有足够的工具和时间，创建Deepfake是一项足够简单的任务；然而，由此产生的Deepfake不够真实，无法完全愚弄检测软件和人类审查员。
Recent advancements in machine learning and computer vision have led to the proliferation of Deepfakes. As technology democratizes over time, there is an increasing fear that novice users can create Deepfakes, to discredit others and undermine public discourse. In this paper, we conduct user studies to understand whether participants with advanced computer skills and varying level of computer science expertise can create Deepfakes of a person saying a target statement using limited media files. We conduct two studies; in the first study (n = 39) participants try creating a target Deepfake in a constrained time frame using any tool they desire. In the second study (n = 29) participants use pre-specified deep learning based tools to create the same Deepfake. We find that for the first study, of the participants successfully created complete Deepfakes with audio and video, whereas for the second user study, of the participants were successful in stitching target speech to the target video. We further use Deepfake detection software tools as well as human examiner-based analysis, to classify the successfully generated Deepfake outputs as fake, suspicious, or real. The software detector classified of the Deepfakes as fake, whereas the human examiners classified of the videos as fake. We conclude that creating Deepfakes is a simple enough task for a novice user given adequate tools and time; however, the resulting Deepfakes are not sufficiently real-looking and are unable to completely fool detection software as well as human examiners.