Attention Map Modification to Improve Deepfake Detection in Unseen Datasets
-
- WATABIKI Ryo
- Aoyama Gakuin University
-
- KANEKO Naoshi
- Aoyama Gakuin University,Tokyo Denki University
-
- SUMI Kazuhiko
- Aoyama Gakuin University
Bibliographic Information
- Other Title
-
- Attention Map修正による未学習のデータセットに対するDeepfake検出性能向上
Abstract
Deepfakes pose serious privacy and disinformation threats. Previous deepfake detection models often suffer from low detection accuracy on unseen datasets that are not used in training. While some studies introduce attention mechanisms to improve explainability and detection accuracy, such models tend to focus on unmanipulated areas, still causing limited accuracy on unseen datasets. This paper proposes a novel method to improve the performance of attention-based deepfake detection models on unseen datasets. Based on self-blended images, we use manipulated area maps as supervision signals of learned attention maps so as to a network is trained to focus on the manipulated areas. We evaluate the performance of the proposed method by testing it on four datasets not used for training. The results show that the proposed method outperforms baseline models by about 2% in the AUC score, achieving the best performance over the state-of-the-art methods.
Journal
-
- 電子電子情報通信学会論文誌A 基礎・境界
-
電子電子情報通信学会論文誌A 基礎・境界 J106-A (12), 275-284, 2023-12-01
The Institute of Electronics, Information and Communication Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1390298278366155008
-
- ISSN
- 18810195
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Disallowed