Answers are grounded in this paper and cite their sources.
We present an exploratory study of how people detect deepfake videos. Through watching a set of real and fake videos, and semi‐structured interviews, participants identified a set of characteristics such as blurred faces and unnatural voices, present in deepfake videos. A list of verification strategies, including checking other sources and repeated viewing, were also derived.
No takes yet. Share an insight, caveat, or question.
Thaw et al. (2020) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: