Summary of Unmasking Illusions: Understanding Human Perception Of Audiovisual Deepfakes, by Ammarah Hashmi et al.
Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes
by Ammarah Hashmi, Sahibzada Adil Shahzad, Chia-Wen Lin, Yu Tsao, Hsin-Min Wang
First submitted to arxiv on: 7 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG); Multimedia (cs.MM)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Machine learning educators can expect this research paper to explore the human ability to discern deepfake videos. The study compares human observers with five state-of-the-art audiovisual deepfake detection models, utilizing a web-based platform and gamification concepts to engage 110 participants in evaluating the authenticity of 40 videos (20 real and 20 fake). Keywords include model names like FakeAVCeleb dataset, methods like gamification, datasets like FakeAVCeleb, tasks like deepfake detection, and relevant subfields like machine learning. The paper highlights human perception’s limitations, as humans tend to overestimate their detection capabilities. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research explores how well people can tell if a video is real or fake. Can we really trust what we see? The study wants to know how good humans are at detecting deepfakes compared to special AI models. They used a fun game-like platform and asked 110 people to watch videos and say which ones were real or fake. They found that the AI models were better at telling apart real from fake videos, but people still thought they could do it better than they actually can. |
Keywords
» Artificial intelligence » Machine learning
