揭开幻象：理解人类对音视频深度伪造的感知
Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes
AI总结：
本文通过主观研究评估人类辨别音视频深度伪造的能力，并与五种先进AI模型对比，发现AI表现优于人类且人类高估自身检测能力，为基准测试和取证分析提供参考。
摘要：
当代深度伪造的出现引起了机器学习研究的广泛关注，因为人工智能（AI）生成的合成媒体增加了被误解的可能性，并且难以与真实内容区分。目前，机器学习技术已被广泛研究用于自动检测深度伪造。然而，人类感知方面的研究较少。恶意深度伪造最终可能导致公共和社会问题。我们人类能否正确感知所观看视频内容的真实性？答案显然是不确定的；因此，本文旨在通过一项主观研究评估人类辨别深度伪造视频的能力。我们通过将人类观察者与五种最先进的音视频深度伪造检测模型进行比较来呈现我们的发现。为此，我们利用游戏化概念为110名参与者（55名英语母语者和55名非英语母语者）提供了一个基于网络的平台，他们可以在该平台上访问一系列40个视频（20个真实和20个伪造）以判断其真实性。每位参与者使用相同的40个视频以不同的随机顺序进行了两次实验。这些视频是从FakeAVCeleb数据集中手动选取的。我们发现，在相同的40个视频上进行评估时，所有AI模型的表现均优于人类。研究还揭示，虽然欺骗并非不可能，但人类往往高估自己的检测能力。我们的实验结果可能有助于对人类与机器性能进行基准测试，推进取证分析，并实现自适应对策。
英文摘要：
The emergence of contemporary deepfakes has attracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content. Currently, machine learning techniques have been extensively studied for automatically detecting deepfakes. However, human perception has been less explored. Malicious deepfakes could ultimately cause public and social problems. Can we humans correctly perceive the authenticity of the content of the videos we watch? The answer is obviously uncertain; therefore, this paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-ofthe-art audiovisual deepfake detection models. To this end, we used gamification concepts to provide 110 participants (55 native English speakers and 55 non-native English speakers) with a webbased platform where they could access a series of 40 videos (20 real and 20 fake) to determine their authenticity. Each participant performed the experiment twice with the same 40 videos in different random orders. The videos are manually selected from the FakeAVCeleb dataset. We found that all AI models performed better than humans when evaluated on the same 40 videos. The study also reveals that while deception is not impossible, humans tend to overestimate their detection capabilities. Our experimental results may help benchmark human versus machine performance, advance forensics analysis, and enable adaptive countermeasures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
