Learning Real Facial Concepts for Independent Deepfake Detection
Authors: Ming-Hui Liu, Harry Cheng, Tianyi Wang, Xin Luo, Xin-Shun Xu
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | extensive experiments on five widely used datasets demonstrate that Real ID significantly outperforms existing state-of-the-art methods, achieving a 1.74% improvement in average accuracy. |
| Researcher Affiliation | Academia | 1School of Software, Shandong University 2School of Computing, National University of Singapore 3College of Computing and Data Science, Nanyang Technological University |
| Pseudocode | No | The paper describes methods using text and mathematical equations but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain an explicit statement about releasing code, nor does it provide a link to a code repository. |
| Open Datasets | Yes | We trained our model with the FF++ dataset [R ossler et al., 2019]. This dataset includes 1,000 real videos from You Tube, as well as five types of manipulated videos yielding a total of 6,000 videos. Finally, to evaluate the generalization capability of our model, we performed the cross-dataset testing on five widely used deepfake datasets, i.e., Celeb-DF [Li et al., 2020b], DFD [Dufour and Gully, 2020], DFDC [Dolhansky et al., 2020], DFDCp [Dolhansky et al., 2020], and UADFV [Li et al., 2018]. |
| Dataset Splits | Yes | Similar to the common setup for generalizable deepfake detection [Wang and Deng, 2021; Fei et al., 2022; Cao et al., 2022], we trained our model with the FF++ dataset [R ossler et al., 2019]. This dataset includes 1,000 real videos from You Tube, as well as five types of manipulated videos yielding a total of 6,000 videos. Finally, to evaluate the generalization capability of our model, we performed the cross-dataset testing on five widely used deepfake datasets, i.e., Celeb-DF [Li et al., 2020b], DFD [Dufour and Gully, 2020], DFDC [Dolhansky et al., 2020], DFDCp [Dolhansky et al., 2020], and UADFV [Li et al., 2018]. |
| Hardware Specification | Yes | We conducted the experiments on a single RTX 3090 GPU with a batch size of 16. |
| Software Dependencies | No | The paper mentions Dlib2, Efficient Net, and ViT as tools or backbones but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | Yes | We conducted the experiments on a single RTX 3090 GPU with a batch size of 16. The backbone we employed is Efficient Net [Tan and Le, 2019]... The hyperparameters λ1, λ2, and λ3 in Equation (15) are selected via grid search and set to 0.6, 1.0, and 1.0, respectively. |