研究人眼对假视频的敏感度，发现视觉瑕疵会降低可信度
Is Seeing Believing? Evaluating Human Sensitivity to Synthetic Video
- 通过三组实验测试视听失真和深度伪造特征对判断的影响
- 视频失真与深度伪造痕迹显著降低内容可信度
- 适合关注虚假信息传播与认知安全的研究者阅读
机器学习进步催生了逼真的合成视频（深伪视频），引发人们对虚假信息泛滥和公众认知操纵的担忧。尽管影响严重，但人类如何感知合成媒体仍不清晰，制约了有效应对策略的制定。本文通过三组被试间实验，研究视听失真及深伪生成画面与配音对认知处理的影响，包括主观可信度评估和客观学习效果。结果表明，视频失真与深伪痕迹会显著降低内容可信度。研究揭示了合成视频感知中的认知机制，强调需进一步发展深伪暴露相关理论。
原文摘要 · Abstract (English)
Advances in machine learning have enabled the creation of realistic synthetic videos known as deepfakes. As deepfakes proliferate, concerns about rapid spread of disinformation and manipulation of public perception are mounting. Despite the alarming implications, our understanding of how individuals perceive synthetic media remains limited, obstructing the development of effective mitigation strategies. This paper aims to narrow this gap by investigating human responses to visual and auditory distortions of videos and deepfake-generated visuals and narration. In two between-subjects experiments, we study whether audio-visual distortions affect cognitive processing, such as subjective credibility assessment and objective learning outcomes. A third study reveals that artifacts from deepfakes influence credibility. The three studies show that video distortions and deepfake artifacts can reduce credibility. Our research contributes to the ongoing exploration of the cognitive processes involved in the evaluation and perception of synthetic videos, and underscores the need for further theory development concerning deepfake exposure.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。