DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection
Open accessThe DOI matches its Crossref record; 84 of the 84 references it cites were found in a registry or an index.
Abstract
Existing deepfake detection methods fail to generalize well to unseen or degraded samples, which can be attributed to the over-fitting of low-level forgery patterns. Here we argue that high-level semantics are also indispensable recipes for generalizable forgery detection. Recently, large pre-trained Vision Transformers (ViTs) have shown promising generalization capability. In this paper, we propose the first parameter-efficient tuning approach for deepfake detection, namely DeepFake-Adapter, to effectively and efficiently adapt the generalizable high-level semantics from large pre-trained ViTs to aid deepfake detection. Given large pre-trained models but limited deepfake data, DeepFake-Adapter introduces lightweight yet dedicated dual-level adapter modules to a ViT while keeping the model backbone frozen. Specifically, to guide the adaptation process to be aware of both global and local forgery cues of deepfake data, 1) we not only insert Globally-aware Bottleneck Adapters in parallel to MLP layers of ViT, 2) but also actively cross-attend Locally-aware Spatial Adapters with features from ViT. Unlike existing deepfake detection methods merely focusing on low-level forgery patterns, the forgery detection process of our model can be regularized by generalizable high-level semantics from a pre-trained ViT and adapted by global and local low-level forgeries of deepfake data. Extensive experiments on several standard deepfake detection benchmarks validate the effectiveness of our approach. Notably, DeepFake-Adapter demonstrates a convincing advantage under cross-dataset and cross-manipulation settings.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Shao et al. [22 ] proposed DeepFake-Adapter, a parameter-efficient framework that augments pre-trained ViTs with dual-level adapters to enhance transferability and domain generalization.”
From Cross-dataset video deepfake detection using Transformer and CNN architectures (2026) · cites this paper as [22]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 3×
“FaceForensics++ (c23) FaceForensics++ (c40) Methods DF FS F2F NT DF FS F2F NT ResNet-50 [23] 98.”
InfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“…we compare the linear separability regarding real/fake faces of FaceForensics++ dataset (Rossler et al., 2019) based on features extracted by Xception (Chollet, 2017) pre-trained on ImageNet-1K (Deng et al., 2009) and ViT-Base (Dosovit-skiy et al., 2020) pre-trained on ImageNet-21K, respectively.”
InfluentialAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472 · cited 10×
“, spatial locality, than Convolutional Neural Networks (CNNs) [14].”
InfluentialGrad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380 · cited 4×
“…we compare the linear separability regarding real/fake faces of FaceForensics++ dataset (Rossler et al., 2019) based on features extracted by Xception (Chollet, 2017) pre-trained on ImageNet-1K (Deng et al., 2009) and ViT-Base (Dosovit-skiy et al., 2020) pre-trained on ImageNet-21K, respectively.”
InfluentialHigh-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 1×
“Following the setting of linear-probe evaluation in Radford et al. (2021), we compare the linear separability regarding real/fake faces of FaceForensics++ dataset (Rossler et al., 2019) based on features extracted by Xception (Chollet, 2017) pre-trained on ImageNet-1K (Deng et al., 2009) and…”
Influential(2017) · Cited by 11,625
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Research works printed but not linked: 13
- Agarap, A.F. (2018). Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375. · arXiv
- Ba, J.L., Kiros, J.R., & Hinton, G.E. (2016). Layer normalization. arXiv preprint arXiv:1607.06450. · arXiv
- Chen, Z., Duan, Y., Wang, W., He, J., Lu, T., Dai, J., & Qiao, Y. (2023). Vision transformer adapter for dense predictions. In: ICLR.
- Dhariwal, P., & Nichol, A. (2021). Diffusion models beat gans on image synthesis. NeurIPS, 34, 8780–8794.
- Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., & Ferrer, C.C. (2020). The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397. · arXiv
- Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. In: NeurIPS, 33, 6840–6851.
- Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). Lora: Low-rank adaptation of large language models. In: ICLR.
- Liu, L., Ren, Y., Lin, Z., & Zhao, Z. (2022). Pseudo numerical methods for diffusion models on manifolds. In: ICLR.
- Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-sne. Journal of machine learning research 9(11).
- Quinn, N.A., & Dhariwal, P. (2021). Improved denoising diffusion probabilistic models. In: ICML, pp. 8162–8171.
- Shao, R., Wu, T., & Liu, Z. (2023). Robust sequential deepfake detection. arXiv preprint arXiv:2309.14991. · arXiv
- Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., & Paluri, M. (2014). C3d: generic features for video analysis. CoRR, abs/1412.0767. · arXiv
- Wang, G., Zhou, J., & Wu, Y. (2020). Exposing deep-faked videos by anomalous co-motion pattern detection. arXiv preprint arXiv:2008.04848. · arXiv
Cited by
A Review of Deepfake Techniques: Architecture, Detection and Datasets
Edwards, P., Nebel, J.-C., Greenhill, D., & Liang, X. (2024) · IEEE Access · doi:10.1109/access.2024.3477257 · Cited by 50
“In the study [56], low and high-level semantic information is used to evaluate how discriminative features provide separability amongst real and fake distributions, trained separately using a pre-trained Xception and ViT network.”
BackgroundMethodInfluentialForgery-Aware Adaptive Learning With Vision Transformer for Generalized Face Forgery Detection
Luo, A., Cai, R., Kong, C., Ju, Y., Kang, X., Huang, J., & Kot, A. C. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3522091 · Cited by 41
“[56] propose a dual-level adapter based detector to capture both global and local low-level manipulation traces for face forgery detection.”
Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark
Xin, Y., Yang, J., Luo, S., Du, Y., Qin, Q., Chen, H., Cen, K., He, Y., Fu, B., Cao, Y., et al. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02864-6 · Cited by 202
Robust Sequential DeepFake Detection
Shao, R., Wu, T., & Liu, Z. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-024-02339-6 · Cited by 36
Self-citationDeepFake detection in the AIGC era: A survey, benchmarks, and future perspectives
Xie, S., Qiao, T., Li, S., Zhang, X., Zhou, J., & Feng, G. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103740 · Cited by 14
Metadata
- Authors
- Shao, R., Wu, T., Nie, L., & Liu, Z.
- Affiliations
- Harbin Institute of Technology (CN)
- Nanyang Technological University (SG)
- Corresponding author
- Liu, Ziwei
- Venue
- International Journal of Computer Vision
- Published
- 2025-01-24
- Volume
- 133
- Issue
- 6
- Pages
- 3613-3628
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W4406804129
- Cited by
- 48
- References
- 79
- Citations by year
- 2026: 21 · 2025: 22
- FWCI
- 15.10
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- International Journal of Computer Vision (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DR-NTU (Nanyang Technological University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, parameter-efficient fine-tuning, vision transformer, high-level semantics, generalization to unseen data, cross-dataset generalization, frozen backbone
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection. https://app.cochat.ai/papers/10.1007/s11263-024-02274-6
- The paper
- Shao, R., Wu, T., Nie, L., & Liu, Z. (2025). DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection. International Journal of Computer Vision. https://doi.org/10.1007/s11263-024-02274-6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.