[论文解读] Testing Human Ability To Detect Deepfake Images of Human Faces

Sergi D. Bray, Shane D. Johnson+1 more|arXiv (Cornell University)|Dec 7, 2022

Ethics and Social Impacts of AI被引用 5

一句话总结

本研究通过一项包含280名参与者的在线调查，评估了人类在四组（包括对照组和干预组）条件下检测StyleGAN2生成的人脸深度伪造图像的能力。尽管信心水平很高，参与者的准确率仅为62%，仅略高于随机猜测水平，且无任何干预显著提升检测能力，凸显了人类在感知合成媒体方面存在严重漏洞。

ABSTRACT

Deepfakes are computationally-created entities that falsely represent reality. They can take image, video, and audio modalities, and pose a threat to many areas of systems and societies, comprising a topic of interest to various aspects of cybersecurity and cybersafety. In 2020 a workshop consulting AI experts from academia, policing, government, the private sector, and state security agencies ranked deepfakes as the most serious AI threat. These experts noted that since fake material can propagate through many uncontrolled routes, changes in citizen behaviour may be the only effective defence. This study aims to assess human ability to identify image deepfakes of human faces (StyleGAN2:FFHQ) from nondeepfake images (FFHQ), and to assess the effectiveness of simple interventions intended to improve detection accuracy. Using an online survey, 280 participants were randomly allocated to one of four groups: a control group, and 3 assistance interventions. Each participant was shown a sequence of 20 images randomly selected from a pool of 50 deepfake and 50 real images of human faces. Participants were asked if each image was AI-generated or not, to report their confidence, and to describe the reasoning behind each response. Overall detection accuracy was only just above chance and none of the interventions significantly improved this. Participants' confidence in their answers was high and unrelated to accuracy. Assessing the results on a per-image basis reveals participants consistently found certain images harder to label correctly, but reported similarly high confidence regardless of the image. Thus, although participant accuracy was 62% overall, this accuracy across images ranged quite evenly between 85% and 30%, with an accuracy of below 50% for one in every five images. We interpret the findings as suggesting that there is a need for an urgent call to action to address this threat.

研究动机与目标

• 评估人类使用StyleGAN2生成的深度伪造人脸图像的检测能力。
• 评估简单干预措施在提升人类检测准确率方面的有效性。
• 考察信心水平与实际检测准确率之间的关系。
• 识别使深度伪造图像特别难以检测的特定图像特征。

提出的方法

• 参与者通过在线调查招募，并被随机分配至四组中的一组：对照组或三种干预条件组。
• 每位参与者从FFHQ数据集中随机查看20张平衡的图像（50张真实图像与50张深度伪造图像）。
• 参与者将每张图像分类为AI生成或真实图像，并报告每项判断的信心程度及理由。
• 按参与者和按图像分别计算检测准确率，并将信心水平与准确率进行相关性分析。
• 通过统计分析比较各组之间的检测表现，以评估干预措施的有效性。
• 逐图像分析识别出被持续误判的图像，揭示人类在特定深度伪造样本上困难的模式。

实验结果

研究问题

• RQ1 使用StyleGAN2生成的深度伪造人脸图像，人类检测的基线准确率是多少？
• RQ2 简单干预是否能显著提升人类检测深度伪造人脸图像的能力？
• RQ3 在识别深度伪造图像时，自我报告的信心程度与实际检测准确率之间有何相关性？
• RQ4 哪些特定的深度伪造图像最常被人类误判？其何种特征使其具有欺骗性？

主要发现

• 总体检测准确率为62%，仅略高于随机猜测水平，表明人类在可靠检测深度伪造图像方面能力较差。
• 与对照组相比，三种干预条件中均未观察到检测准确率的显著提升。
• 参与者对其判断表现出高度信心，但这种信心与实际准确率之间无显著相关性。
• 每张图像的检测准确率差异极大，范围在30%至85%之间，其中五分之一的图像准确率低于50%。
• 某些深度伪造图像在参与者中持续被误判，表明存在特定的视觉伪影或模式，可逃避人类感知。
• 研究结果表明人类感知存在系统性漏洞，凸显了亟需通过技术与教育手段应对深度伪造威胁。