딥페이크 영상 학습을 위한 데이터셋 평가기준 개발
Development of Dataset Evaluation Criteria for Learning Deepfake Video
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
As Deepfakes phenomenon is spreading worldwide mainly through videos in web platforms and it is urgent to address the issue on time. More recently, researchers have extensively discussed deepfake video datasets. However, it has been pointed out that the existing Deepfake datasets do not properly reflect the potential threat and realism due to various limitations. Although there is a need for research that establishes an agreed-upon concept for high-quality datasets or suggests evaluation criterion, there are still handful studies which examined it to-date. Therefore, this study focused on the development of the evaluation criterion for the Deepfake video dataset. In this study, the fitness of the Deepfake dataset was presented and evaluation criterions were derived through the review of previous studies. AHP structuralization and analysis were performed to advance the evaluation criterion. The results showed that Facial Expression, Validation, and Data Characteristics are important determinants of data quality. This is interpreted as a result that reflects the importance of minimizing defects and presenting results based on scientific methods when evaluating quality. This study has implications in that it suggests the fitness and evaluation criterion of the Deepfake dataset. Since the evaluation criterion presented in this study was derived based on the items considered in previous studies, it is thought that all evaluation criterions will be effective for quality improvement. It is also expected to be used as criteria for selecting an appropriate deefake dataset or as a reference for designing a Deepfake data benchmark. This study could not apply the presented evaluation criterion to existing Deepfake datasets. In future research, the proposed evaluation criterion will be applied to existing datasets to evaluate the strengths and weaknesses of each dataset, and to consider what implications there will be when used in Deepfake research.
Abstract
As Deepfakes phenomenon is spreading worldwide mainly through videos in web platforms and it is urgent to address the issue on time. More recently, researchers have extensively discussed deepfake video datasets. However, it has been pointed out that the existing Deepfake datasets do not properly reflect the potential threat and realism due to various limitations. Although there is a need for research that establishes an agreed-upon concept for high-quality datasets or suggests evaluation criterion, there are still handful studies which examined it to-date. Therefore, this study focused on the development of the evaluation criterion for the Deepfake video dataset. In this study, the fitness of the Deepfake dataset was presented and evaluation criterions were derived through the review of previous studies. AHP structuralization and analysis were performed to advance the evaluation criterion. The results showed that Facial Expression, Validation, and Data Characteristics are important determinants of data quality. This is interpreted as a result that reflects the importance of minimizing defects and presenting results based on scientific methods when evaluating quality. This study has implications in that it suggests the fitness and evaluation criterion of the Deepfake dataset. Since the evaluation criterion presented in this study was derived based on the items considered in previous studies, it is thought that all evaluation criterions will be effective for quality improvement. It is also expected to be used as criteria for selecting an appropriate deefake dataset or as a reference for designing a Deepfake data benchmark. This study could not apply the presented evaluation criterion to existing Deepfake datasets. In future research, the proposed evaluation criterion will be applied to existing datasets to evaluate the strengths and weaknesses of each dataset, and to consider what implications there will be when used in Deepfake research.
참고문헌 (37)
- Dolhansky, B., "The Deepfake detection challenge(dfdc)preview dataset", arXiv preprint arXiv : 1910. 08854, ~ (2019)
- Dolhansky, B., "The Deepfake detection challenge(dfdc)dataset", arXiv preprint arXiv : 2006. 07397, ~ (2020)
- Đorđević, M., "Deepfake video analysis using SIFT features", 201927th Telecommunications Forum (TELFOR), IEEE, pp.1~4 (2019)
- "Contributing data to deep-fake detection research" (2019)[URL]
- Feng, K., "A Detect method for Deepfake video based on full face recognition", 2020IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), IEEE, 1, pp.1121~1125 (2020)
- Guarnera, L., "Fighting Deepfake by exposing the convolutional traces on images", IEEE Access, 8, pp.165085~165098 (2020)
- Jiang, L, "Deeperforensics-1.0: A large-scale dataset for real-world face forgery detection", Proceedings of the IEEE, 2020, 2889~2898
- Karras, T., "Progressive growing of gans for improved quality, stability, and variation", and variation. arXiv preprint arXiv : 1710. 10196, ~ (2017)
- 김형섭, "데이터 품질관리 평가 모델에 관한 연구", 한국융합학회논문지, 11(7), pp.217~222 (2020), 한국융합학회[DOI]
- 김태구, "AHP를 활용한 철도교통 분야 R&D 실용화 촉진점검 체크리스트 개발", 한국경영공학회지, 22(1), pp.77~87 (2017), 한국경영공학회[DOI]
- KOREA Data Agency, "Guideline for data quality management(Ver 2.1)", ~ (2006)
- Korshunov, P., "Vulnerability assessment and detection of Deepfake videos", 2019 International Conference on Biometrics (ICB), IEEE, pp.1~6 (2019)
- Kwon, P., "KoDF : A Large-scale Korean Deepfake Detection Dataset", arXiv preprint arXiv : 2103. 10094, ~ (2021)
- Le, T. N, "OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild", Proceedings of the IEEE, 2021, 10117~10127
- Li, Y., "Exposing Deepfake videos by detecting face warping artifacts", ArXiv Preprint ArXiv : 1811. 00656, ~ (2018)
- Li, Y, "Celeb-df:A large-scale challenging dataset for Deepfake forensics", Proceedings of the IEEE, 2020, 3207~3216
- Mahfoudi, G., "DEFACTO: Image and face manipulation dataset", 2019 27th European Signal Processing Conference (EUSIPCO), IEEE, pp.1~5 (2019)
- Matern, F., "Exploiting visual artifacts to expose Deepfakes and face manipulations", 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW), IEEE, pp.83~92 (2019)
- National Information Society Agency, "Guideline for artificial intelligence learning data quality management", ~ (2020)
- 박고은, "공공개방데이터 품질 특성에 관한 연구", 디지털융복합연구, 13(10), pp.135~146 (2015), 한국디지털정책학회[DOI]
- Ramadhani, K. N., "A Comparative Study of Deepfake Video Detection Method", 2020 3rd International Conference on Information and Communications Technology (ICOIACT), IEEE, pp.394~399 (2020)
- Rossler, A, "Faceforensics++: Learning to detect manipulated facial images", Proceedings of the IEEE, 2019, 1~11
- Saaty, T. L., "Axiomatic foundation of the analytic hierarchy process", Management Science, 32(7), pp.841~855 (1986)
- Tayseer, M., "Digital Forensics and Analysis of Deepfake Videos", 11th International Conference on Information and Communication Systems (ICICS) (2020)
- Thies, J., "Deferred neural rendering, Image synthesis using neural textures", ACM Transactions on Graphics (TOG), 38(4), pp.1~12 (2019)
- Thies, J, "Face2face: Real-time face capture and reenactment of rgb videos", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2387~2395 (2016)
- Tolosana, R., "Deepfakes and beyond : A survey of face manipulation and fake detection", Information Fusion, 64, pp.131~148 (2020)
- Verdoliva, L., "Media Forensics and Deepfakes : An Overview", IEEE Journal of Selected Topics in Signal Processing, 14(5), pp.910~932 (2020)
- Wang, R., "Fakespotter : A simple yet robust baseline for spotting ai-synthesized fake faces", ArXiv Preprint ArXiv : 1909. 06122, ~ (2019)
- Wang, T.C, "High-resolution image synthesis and semantic manipulation with conditional gans", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.8798~8807 (2018)
- 양재용, "IT-BSC와 AHP를 사용한 유통매장 전자가격정보시스템 도입 전후 성과요인의 Priority-Gap 측정에 관한 연구", 경영정보학연구, 22(2), pp.53~76 (2020), 한국경영정보학회
- Youm, G. Y., "SAR image target recognition research trend using deep learning", The Journal of The Korean Institute of Communication Sciences, 34(7), pp.31~39 (2017)
- Yu, P, "A Survey on Deepfake Video Detection", IET Biometrics (2016)
- 윤창희, "인공지능 데이터 품질검증 기술 및 오픈소스 프레임워크 분석 연구", 멀티미디어학회논문지, 24(10), pp.1403~1413 (2021), 한국멀티미디어학회
- Zi, B., "WildDeepfake: A challenging real-world dataset for Deepfake detection", Proceedings of the 28th ACM International Conference on Multimedia, pp.2382~2390 (2020)
- "UCI Machine Learning Repository"[URL]
- "Kaggle"[URL]