Seeing is Believing: Exploring Perceptual Differences in DeepFake Videos

要旨

With AI on the boom, DeepFakes have emerged as a tool with a massive potential for abuse. The hyper-realistic imagery of these manipulated videos coupled with the expedited delivery models of social media platforms gives deception, propaganda, and disinformation an entirely new meaning. Hence, raising awareness about DeepFakes and how to accurately flag them has become imperative. However, given differences in human cognition and perception, this is not straightforward. In this paper, we perform an investigative user study and also analyze existing AI detection algorithms from the literature to demystify the unknowns that are at play behind the scenes when detecting DeepFakes. Based on our findings, we design a customized training program to improve detection and evaluate on a treatment group of low-literate population, which is most vulnerable to DeepFakes. Our results suggest that, while DeepFakes are becoming imperceptible, contextualized education and training can help raise awareness and improve detection.

著者
Rashid Tahir
University of Prince Mugrin, Medina, Saudi Arabia
Brishna Batool
Lahore University of Management Sciences, Lahore, Pakistan
Hira Jamshed
Lahore University of Managements Sciences, Lahore, Pakistan
Mahnoor Jameel
Lahore University of Managements Sciences, Lahore, Pakistan
Mubashir Anwar
Lahore University of Managements Sciences, Lahore, Pakistan
Faizan Ahmed
University of Virginia, Charlottesville, Virginia, United States
Muhammad Adeel Zaffar
Lahore University of Management Sciences, Lahore, Pakistan
Muhammad Fareed. Zaffar
Lahore University of Management sciences, Lahore, Pakistan
DOI

10.1145/3411764.3445699

論文URL

https://doi.org/10.1145/3411764.3445699

動画

会議: CHI 2021

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2021.acm.org/)

セッション: Trust, Transparency & Sharing Online

[B] Paper Room 07, 2021-05-14 01:00:00~2021-05-14 03:00:00 / [C] Paper Room 07, 2021-05-14 09:00:00~2021-05-14 11:00:00 / [A] Paper Room 07, 2021-05-13 17:00:00~2021-05-13 19:00:00
Paper Room 07
14 件の発表
2021-05-14 01:00:00
2021-05-14 03:00:00
日本語まとめ
読み込み中…