arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.05985cs.CV
收藏

超越检测:深度伪造的视觉真实度评估

Beyond Detection: Visual Realism Assessment of Deepfakes

University of Ljubljana(卢布尔雅那大学)

Luka Dragar, Peter Peer, Vitomir Štruc, Borut Batagelj

AI总结:

针对深度伪造技术带来的安全隐私问题,提出基于Eva和ConvNext卷积神经网络集成的深度伪造视频视觉真实度评估方法,在IJCB 2023同期的DFGC竞赛中获第三名。

摘要:

在数字化快速发展与人工智能不断进步的时代,DeepFake(深度伪造)技术的发展带来了严重的安全与隐私隐患。本文提出了一种评估DeepFake视频视觉真实度的有效方法。我们采用由两个卷积神经网络(CNN)模型——Eva与ConvNext组成的集成模型,这些模型在DeepFake Game Competition(深度伪造游戏竞赛,DFGC)2022数据集上训练,旨在基于从帧序列中提取的特征,预测DeepFake视频的平均意见得分(MOS)。我们的方法在2023年国际生物识别联合会议(IJCB 2023)同期举办的最新一届视觉真实度评估DFGC竞赛中获得第三名。本文概述了模型结构、数据预处理与训练流程,还报告了我们的模型相较于竞赛基线模型的性能,并讨论了研究发现的意义。

英文摘要:

In the era of rapid digitalization and artificial intelligence advancements, the development of DeepFake technology has posed significant security and privacy concerns. This paper presents an effective measure to assess the visual realism of DeepFake videos. We utilize an ensemble of two Convolutional Neural Network (CNN) models: Eva and ConvNext. These models have been trained on the DeepFake Game Competition (DFGC) 2022 dataset and aim to predict Mean Opinion Scores (MOS) from DeepFake videos based on features extracted from sequences of frames. Our method secured the third place in the recent DFGC on Visual Realism Assessment held in conjunction with the 2023 International Joint Conference on Biometrics (IJCB 2023). We provide an over\-view of the models, data preprocessing, and training procedures. We also report the performance of our models against the competition's baseline model and discuss the implications of our findings.

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。

↑