Can We Leave Deepfake Data Behind in Training Deepfake Detector?
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
The generalization ability of deepfake detectors is vital for their applications in real-world scenarios. One effective solution to enhance this ability is to train the models with manually-blended data, which we termed "blendfake", encouraging models to learn generic forgery artifacts like blending boundary. Interestingly, current SoTA methods utilize blendfake without incorporating any deepfake data in their training process. This is likely because previous empirical observations suggest that vanilla hybrid training (VHT), which combines deepfake and blendfake data, results in inferior performance to methods using only blendfake data (so-called "1+1<2"). Therefore, a critical question arises: Can we leave deepfake behind and rely solely on blendfake data to train an effective deepfake detector? Intuitively, as deepfakes also contain additional informative forgery clues (e.g., deep generative artifacts), excluding all deepfake data in training deepfake detectors seems counter-intuitive. In this paper, we rethink the role of blendfake in detecting deepfakes and formulate the process from "real to blendfake to deepfake" to be a progressive transition. Specifically, blendfake and deepfake can be explicitly delineated as the oriented pivot anchors between "real-to-fake" transitions. The accumulation of forgery information should be oriented and progressively increasing during this transition process. To this end, we propose an Oriented Progressive Regularizor (OPR) to establish the constraints that compel the distribution of anchors to be discretely arranged. Furthermore, we introduce feature bridging to facilitate the smooth transition between adjacent anchors. Extensive experiments confirm that our design allows leveraging forgery information from both blendfake and deepfake effectively and comprehensively.
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
“This strategy helps the model to learn a more structured representation of forgery artifacts rather than treating each type as disconnected examples.”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [169]
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Yan, Z., Zhao, Y., Shen, C., Guo, M., Fu, X., Yao, T., Ding, S., Wu, Y., & Li, Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01177 · Cited by 116
Self-citationX2-DFD: A framework for explainable and extendable Deepfake Detection
Chen, Y., Yan, Z., Cheng, G., Zhao, K., Lyu, S., & Wu, B. (2025) · neural information processing systems · doi:10.52202/085713-2809 · Cited by 57
Self-citationDeepfake Detection that Generalizes Across Benchmarks
Yermakov, A., Čech, J., Matas, J., & Fritz, M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00082 · Cited by 68
Nguyen-Le, H.-H., Tran, V.-T., Nguyen, D.-T., & Le-Khac, N.-A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11608-4 · Cited by 28
Kundu, R., Xiong, H., Mohanty, V., Balachandran, A., & Roy–Chowdhury, A. K. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02612 · Cited by 57
From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes
Ma, L., Yan, Z., Xu, J., Chen, Y., Guo, Q., Bi, Z., Liao, Y., & lin, H. (2025) · neural information processing systems · doi:10.52202/085713-2330 · Cited by 33
Self-citationStacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection
Cheng, J., Yan, Z., Zhang, Y., Hao, L., Ai, J., Zou, Q., Chen, L., & Wang, Z. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01300 · Cited by 33
Self-citationFORGE: Forensic Reasoning with Grounded Evidence
Kundu, R., Jia, S., Mohanty, V., Balachandran, A., & Roy–Chowdhury, A. K. (2026) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/2026.findings-emnlp.2054 · Cited by 18
Du, Y., Wang, Z., Luo, Y., Piao, C., Yan, Z., Li, H., & Yuan, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.15233 · Cited by 21
Self-citationZhang, X., Zhu, P., Zhang, C., Yan, Z., Cheng, J., Lao, M., Cai, S., & Guo, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00362 · Cited by 26
Self-citationA Quality-Centric Framework for Generic Deepfake DetectionPreprint
Song, W., Yan, Z., Lin, Y., Yao, T., Chen, C., Chen, S., Zhao, Y., Ding, S., & Li, B. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.05335 · Cited by 13
Self-citationSynthetic Artwork Authentication Threats: Detection by Combining Neural Network and Blockchain
Kearns, L., Alam, A., & Allison, J. (2025) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70225 · Cited by 6
Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges
Liu, P., Tao, Q., & Zhou, J. T. (2024) · arXiv · doi:10.48550/arxiv.2406.06965 · Cited by 6
DFREC: DeepFake Identity Recovery Based on Identity-Aware Masked Autoencoder
Yu, P., Gao, H., Fei, J., Huang, Z., Xia, Z., & Chang, C.-H. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3683283 · Cited by 6
Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
Lin, K., Yan, Z., Zhang, K.-Y., Li, H., Zhou, Y., Lin, Y., Li, W., Yao, T., Ding, S., & Li, B. (2025) · neural information processing systems · doi:10.52202/085713-4613 · Cited by 10
Self-citationPrabhu, O., Naik, S. S., Prarthana, B. K., Prabhu, S., & Chadaga, K. (2026) · Systems and Soft Computing · doi:10.1016/j.sasc.2026.200476 · Cited by 6
Fact or Fake? Assessing the Role of Deepfake Detectors in Multimodal Misinformation Detection
Sagar, A. S. S., Bennamoun, M., Boussaid, F., Sharif, N., Xu, L., Sahmoud, S. A., & Kishk, A. (2026) · IEEE Access · doi:10.1109/access.2026.3686437 · Cited by 2
DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis
Cai, Y., Li, J., Li, Z., Chen, W., Lan, R., Xie, X., Luo, X., & Li, G. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01164 · Cited by 18
Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery DetectionPreprint
Lai, Y., Yu, Z., Wang, J., Shen, L., Xu, Y. D., & Cao, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.12546 · Cited by 9
SSD: Making Face Forgery Clues Evident Again With Self-Steganographic Detection
Xia, R., Zhou, D., Yuan, L., Li, J., Wang, N., & Gao, X. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3667180 · Cited by 4
Explainable Deepfake Detection with RL Enhanced Self-Blended Images
Jiang, N., Zeng, D., Liu, Y., Yi, H., Yu, S., Weng, M., Shen, H., & Li, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464556 · Cited by 4
SAGA: Source Attribution of Generative AI VideosPreprint
Kundu, R., Mohanty, V., Xiong, H., Jia, S., Balachandran, A., & Roy–Chowdhury, A. K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.12834 · Cited by 5
SELFI: Selective Fusion of Identity for Generalizable Deepfake DetectionPreprint
Kim, Y., Jang, M., Kwon, M.-J., Lee, W., & Kim, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.17592 · Cited by 4
Cui, J., Du, J., Li, Y., Gao, L., Jiang, H., & Bao, C. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755137 · Cited by 2
SAFE: Semantic- and Frequency-Enhanced Curriculum for Cross-Domain Deepfake Detection
Yao, Y., Zheng, K., Wu, B., Wu, C., Wang, J., Gao, J., Yang, M., & Luo, D. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i14.38179 · Cited by 3
Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation
Chou, Y., Yu, T., Huang, W., ZhangYuHeng, Dai, T., & Xia, S. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i5.37334 · Cited by 11
Suppressing Gradient Conflict for Generalizable Deepfake Detection
Liu, M.-H., Cheng, H. H., Luo, X., & Xu, X. G. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3687009 · Cited by 2
Liu, J., Shi, H., Zhang, Y., & Zhang, X. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754984 · Cited by 3
Self-citationIDRetracor: Towards Visual Forensics against Malicious Face Swapping
Cheng, J., Ai, J., Han, Z., Liang, C., Zou, Q., & Wang, Z. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3774429 · Cited by 1
Self-citationComponent-Specific Prompt Tuning for Deepfake Detection
Chen, Y., Guo, H., Peng, C., Wang, N., & Gao, X. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3678021 · Cited by 2
Deepfake Detection via Exploring Degradation Inconsistency
Bai, W., Liu, Y., Zhang, A., Wang, Y., Li, B., Hu, W., & Zhang, Z. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3695433 · Cited by 2
HCSI-Net: Hierarchical Cross-Stream Interaction for Generalizable Deepfake Detection
Brodarić, M., Ivanovska, M., Jain, D. K., Peer, P., & Štruc, V. (2026) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf68042.2026.11558171 · Cited by 1
A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real WorldPreprint
Cheng, J., Yan, R., Yan, Z., Gan, Y., Zhang, X., Wang, Z., Peng, W., & Liang, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.04837 · Cited by 2
Self-citationAdvances in Deepfake Detection: Technologies, Methods and Future Directions
Tejaswi, S., Babu, T., & Tejaswi, K. (2025) · International Conference on Data Science and Business Systems (ICDSBS) · doi:10.1109/icdsbs63635.2025.11032017 · Cited by 2
A Hybrid Model for Generalizable Deepfake Detection via Blending, Semantic, and General Artifacts
Le-Phan, M.-K., Le, M.-H., Tran, M., & Do, T.-L. (2025) · doi:10.1145/3709020.3734833
Identity-Agnostic Incremental Learning Framework for Face Forgery Detection
Deng, J., Tang, S., Xu, K., & He, P. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5679-3_31
Adaptive Consensus Multi-Teacher Distillation for Generalizable Face Forgery Detection
Jing, J., Sun, F., Peng, C., Liu, D., Wang, N., & Gao, X. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3668432
Supervised Anomaly Detection for Generalized Deepfake Detection
Lu, L., & Gao, G. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3669841
Aljabri, J. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00654-1
DEEPSHIELD: A Multimodal Deep Learning Model for Audio-Visual Deepfake Detection
Naveed, S. J., Alif, A. I., & Saha, S. C. (2026) · International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE) · doi:10.1109/icecte69292.2026.11429232
Hou, S., Jiang, X., Xu, K., Xu, Q., Sun, T., & Meng, L. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3678982
Fair face forgery detection via cross-domain decoupling and entropy-adaptive enhancement
Cheng, F., Tian, L., Meng, F., Wang, X., Peng, M., Su, L., & Wu, Z. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113673
Decoupling Orthogonal Lip Features Against Generative Imposters
Chen, B., Zhu, H., Liang, S., & Wang, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462571
Dynamic Frequency Domain Curriculum Learning: A Novel Framework for Adaptive Image Forgery Detection
Yao, Y., Zheng, K., Wu, B., Wu, C., Wang, J., Gao, J., & Yang, M. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464347
Serackis, A., Jankauskas, M., Grubinskienė, A., & Abromavičius, V. (2026) · Applied Sciences · doi:10.3390/app16115364
Silamanthula, H. K., Thunga, Y. B., Bapana, H., & Malakari, S. B. (2026) · International Journal of Applied Resilience and Sustainability · doi:10.70593/deepsci.0203011
Sun, R., Zhang, Y., Yu, X., Li, M., & Gao, J. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3712721 · Cited by 1
Self-citationZhang, L., Peng, S., Xu, M., & Lu, T. (2026) · Sensors · doi:10.3390/s26144512
Generalizable Deepfake Detection via Simplicity-Bias-Aware CLIP Adaptation
Yahchouchi, C., Roggero, N., Saroul, L., & Dantcheva, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31438-3_38 · Cited by 1
Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detection
Shoaib, S., Borigi, A., Lekkala, R., Lendasse, A., Ratner, E. R., Bhamidipati, S. S., Schlager, A., & Lindner, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38407-2_23
Pang, G., Cheung, Y., Li, R., & Su, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37095-2_2
Exploiting Hierarchical Representations of Vision Foundation Models for Face Forgery Detection
Zhao, Y., Zhu, S., Liu, J., Li, H., Wei, Y., & Guo, Y. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684740
Cheng, Y., Bian, S., Li, L., Zhang, J., Xie, X., & Wang, C. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134494
REALIS: A Curated Dataset for Studying the Challenges of AI Image DetectionPreprint
Gushchin, A., Abud, K., Bychkov, G., Shumitskaya, E., Filippov, A., Lavrushkin, S., Vatolin, D. S., & Antsiferova, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.32734
Leveraging Unlabeled Data from Unknown Sources via Dual-Path Guidance for Deepfake Face Detection
Yang, Z., Tao, R., Zhang, C., Yang, G., Zheng, X., & Zhao, Y. (2026) · doi:10.1109/cvprf71909.2026.00777
Nassar, M. O. (2026) · International Journal of Modern Education and Computer Science · doi:10.5815/ijmecs.2026.05.03
RLDF: A Region-Level Deepfake Dataset and Benchmark for Partial-Face Manipulation DetectionPreprint
Reddy, S., & Das, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.21438
Yang, Y., Zhang, X., Baoxin, F., Huang, C., Lao, M., Gang, L., & Guo, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7650127
CORED: Two-Stage Process Optimization for Consistent Reasoning in Deepfake Detection
Mou, X., & Xiao, B. (2026) · IEEE International Conference on Signal and Image Processing · doi:10.1109/icsip70099.2026.11744246
F 2 -Adapter: A Focus-and-Forget Framework for Generalizable CLIP-based Face Forgery Detection
Gao, Z., Duan, X., Hu, N., Jia, H., Zhao, Y., & Liu, C. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835895
Frequency-Aware Content-Adaptive Multi-scale Learning for Deepfake Detection
Lai, N., Dewi, D. A., Maidin, S. S., Chen, Y., Xiao, W., Zhang, J., Zhang, C., & Hu, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-7201-3_37
Metadata
- Authors
- Cheng, J., Yan, Z., Zhang, Y., Luo, Y., Wang, Z., & Li, C.
- Venue
- Advances in Neural Information Processing Systems 37
- Published
- 2024
- Pages
- 21979-21998
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W4415798721
- Cited by
- 29
- References
- 0
- Citations by year
- 2026: 25 · 2025: 4
- FWCI
- 6.01
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- public-domain
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion, public-domain)
- arXiv (Cornell University) (public-domain)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- deepfake detection, synthetic data, data bias, generative adversarial networks, training data quality
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
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.