The DOI matches its Crossref record; 86 of the 86 references it cites were found in a registry or an index; 23 of the 43 sources its claims cite were checked for support.
AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
Open accessAbstract
Introduces an audio-visual deepfake localization dataset with more than 1M videos and content-driven video, audio, and audio-visual manipulations for more than 2K subjects.
Overview
CoChat Summary
TL;DR
AV-Deepfake1M is a large audiovisual deepfake dataset built with an LLM-driven, three-stage pipeline for transcript, audio, and video manipulation. The paper argues that it is more diverse and harder than prior datasets, and its benchmarks show substantial performance drops for existing detection/localization methods.
Key findings
- The dataset contains 1,886 hours of audio-visual data from 2,068 unique subjects and 1,146,760 videos total, including 286,721 real and 860,039 fake videos.
- Compared with LAV-DF, the paper reports much higher generated-media quality: audio quality for AV-Deepfake1M has SECS 0.991, SNR 9.39, FAD 0.088 overall, and visual quality has PSNR 39.49, SSIM 0.977, FID 0.49 overall.
- Human detection is substantially harder on AV-Deepfake1M than on LAV-DF: user-study accuracy drops from 84.03 to 68.64, AP@0.1 from 36.80 to 15.32, AP@0.5 from 14.17 to 1.92, and AR@1 from 10.04 to 2.54.
- Existing methods perform much worse on AV-Deepfake1M than on LAV-DF; for example, temporal localization AP@0.5 drops from 79.15 to 37.37 for BA-TFD, from 96.30 to 44.42 for BA-TFD+, and from 98.83 to 51.64 for UMMAFormer.
Methods
- The paper constructs AV-Deepfake1M from VoxCeleb2 videos using a three-stage pipeline: transcript manipulation, audio generation, and video generation.
- Transcript manipulation uses ChatGPT via LangChain to perform replace, delete, and insert operations; the number of modifications is set by M = ceil(t / 10), where *t* is video length in seconds.
- Audio is generated with VITS for some subjects and YourTTS for others; video is generated with TalkLip. The dataset is split into 1,657 train subjects, 411 test subjects, and validation sampled from train; benchmarks evaluate localization and detection with multiple SOTA methods and metrics such as AP/AR and AUC/Acc.
Limitations
- The paper explicitly states that, like other deepfake datasets, AV-Deepfake1M has a misbalance in the number of fake and real videos.
- Evident from the text: the test set is restricted to VITS-based identity-dependent audio samples, so not all generation settings appear in test evaluation.
- Evident from the text: the dataset and benchmarks are oriented to content-driven manipulations on faces/audio-visual speech, so the scope is narrower than general deepfake types.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
8 Valid · 5 Not valid · 6 Not checked · 47 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“We investigated several face reenactment strategies including EAMM [26], AVFR-GAN [2], DiffTalk [54], ADNeRF [20] and ATVGnet [10] and concluded that these methods are not well suited for zero-shot lip-synced generation of unseen speakers.”
What the sources say
- Supportedcites [26] [26] Xinya Ji, Hang Zhou, Kaisiyuan Wang, Qianyi Wu, Wayne Wu, Feng Xu, and Xun Cao. 2022. EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model. In ACM SIGGRAPH 2022 Conference Proceedings (SIGGRAPH '22) . Association for Computing Machinery, New York, NY, USA, 1-10. - source
The citation is attached to the enumeration of methods the citing authors themselves investigated, so what is attributed to this source is that EAMM is one of those face-reenactment/talking-face strategies. Our copy supports that: the Abstract states EAMM 'generate[s] one-shot emotional talking faces by involving an emotion source video' via an 'Audio2Facial-Dynamics module ... audio-driven unsupervised zero- and first-order key-points motion', and Section 2 (Related Work) frames it within audio-driven talking face generation and video-driven facial animation, where 'a video [is used] to reenact facial motion ... Our model is built upon a similar idea.' The judgement that such methods are 'not well suited for zero-shot lip-synced generation of unseen speakers' is the citing authors' own conclusion, not a point this source makes or contradicts; Section 4.4 Limitations records EAMM's own stated constraints (needs an emotion source video, unnatural transfer of personalised emotion patterns, mouth-region emotion weak), which is consistent rather than contrary. (LLM, conf=0.80)
- Partly supportedcites [2] [2] Madhav Agarwal, Rudrabha Mukhopadhyay, Vinay P. Namboodiri, and C. V. Jawahar. 2023. Audio-Visual Face Reenactment. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision . 5178-5187. - sourceExperimental — accuracy not yet measured
Our copy confirms only the identification part: AVFR-GAN is indeed a face reenactment method (Abstract, p.1; Introduction, p.1) and the paper does criticise prior single-modality audio- and video-driven works as lacking fine-grained control and having 'loopy head motion' (Related Work, p.2). However, the paper never mentions EAMM, DiffTalk, ADNeRF or ATVGnet, and nowhere states that these strategies are unsuited to zero-shot lip-synced generation of unseen speakers; on the contrary, its Cross-identity Reenactment section and Table 1 report AVFR-GAN achieving the best FID and second-best Sync (behind PC-AVS) on unseen identity pairs. So the 'not well suited for zero-shot lip-synced generation of unseen speakers' characterisation attributed here is not this source's claim (it is the citing authors' own conclusion). (LLM, conf=0.72)
- Disputedcites [54] [54] Shuai Shen, Wenliang Zhao, Zibin Meng, Wanhua Li, Zheng Zhu, Jie Zhou, and Jiwen Lu. 2023. DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 1982-1991. - sourceExperimental — accuracy not yet measured
Our copy of DiffTalk states the opposite of what the citing sentence attributes to it: in Sec. 4.3 (Comparison with 3D-based Methods) it says 'AD-NeRF is a non-general method. In contrast, our method is able to handle unseen identities without further fine-tuning,' and the Introduction and Abstract repeatedly present DiffTalk as synthesizing high-fidelity talking videos 'for novel identities without any further fine-tuning' — i.e. generalized/zero-shot unseen-speaker synthesis is the paper's stated contribution, not a limitation. Its Related Work (Sec. 2) and Introduction also describe 2D-based GAN approaches as performing 'competently on model generalization,' with their shortcoming being image quality and resolution rather than failure on unseen speakers, so the blanket 'not well suited for zero-shot lip-synced generation of unseen speakers' characterization contradicts this source. (EAMM and AVFR-GAN are not discussed in our copy at all, but the DiffTalk attribution is directly refuted.) (LLM, conf=0.85)
Checked by a reasoning model — may be wrong.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Following previous deepfake dataset generation research [6, 31], the dataset includes three different combinations of modified modalities in the generated fake videos.”
What the sources say
- Supportedcites [6] [6] Zhixi Cai, Kalin Stefanov, Abhinav Dhall, and Munawar Hayat. 2022. Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization. In 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA) . Sydney, Australia, 1-10. - source
In A. Data Generation (p. 4), the cited paper describes three variations in its LAV-DF dataset: fake audio and fake video, fake audio and real video, and real audio and fake video. This supports the citation to previous dataset-generation research using those three combinations. (LLM, conf=0.90)
- Supportedcites [31] [31] Hasam Khalid, Shahroz Tariq, and Simon S. Woo. 2021. FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset. arXiv: 2108.05080 [cs]. - source
The citation is attached to “previous deepfake dataset generation research,” not offered as evidence about AV-Deepfake1M itself. FakeAVCeleb’s Introduction (p. 2) says it contains three types of audio-video deepfakes, and its dataset description (p. 6) identifies the three combinations of real and fake audio and video. (LLM, conf=0.92)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“For classification (Table 10), the performance of Xception [12], LipForensics [21], Face X-Ray [36], and SBI [56] also drops compared to LAV-DF.”
What the sources say
- Not checked — no full text of the sourcecites [12] [12] Francois Chollet. 2017. Xception: Deep Learning With Depthwise Separable Convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 1251-1258. - source
- Supportedcites [21] [21] Alexandros Haliassos, Konstantinos Vougioukas, Stavros Petridis, and Maja Pantic. 2021. Lips Don't Lie: A Generalisable and Robust Approach To Face Forgery Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 5039-5049. - source
The Introduction (p. 2) explicitly names the paper's approach LipForensics. In the citing sentence, [21] identifies LipForensics among the methods compared; the AV-Deepfake1M versus LAV-DF result is attributed to the citing paper's Table 10, not to this source. (LLM, conf=0.90)
- Not checked — no full text of the sourcecites [36] [36] Lingzhi Li, Jianmin Bao, Ting Zhang, Hao Yang, Dong Chen, Fang Wen, and Baining Guo. 2020. Face X-Ray for More General Face Forgery Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 5001-5010. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Every source the paper cites for this claim was checked and supports it.
In the paper
“There is a significant drop in BA-TFD [6] temporal localization performance as compared to LAV-DF (Table 8).”
What the sources say
- Supportedcites [6] [6] Zhixi Cai, Kalin Stefanov, Abhinav Dhall, and Munawar Hayat. 2022. Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization. In 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA) . Sydney, Australia, 1-10. - source
The citation is attached to BA-TFD, identifying the method used in the citing paper’s comparison. The source paper’s abstract (p. 1) names its baseline method Boundary Aware Temporal Forgery Detection (BA-TFD), and the Introduction (p. 2) says the authors propose it. The AV-Deepfake1M comparison is presented as the citing paper’s Table 8 result, not as a result attributed to this source. (LLM, conf=0.93)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The output quality of the visual generator Wav2Lip [46] and audio generator SV2TTS [27] used for generating LAV-DF is not sufficient for state-of-the-art detection methods.”
What the sources say
- Supportedcites [46] [46] K R Prajwal, Rudrabha Mukhopadhyay, Vinay P. Namboodiri, and C.V. Jawahar. 2020. A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild. In Proceedings of the 28th ACM International Conference on Multimedia (MM '20) . Association for Computing Machinery, New York, NY, USA, 484-492. - source
The citation [46] immediately follows “Wav2Lip,” identifying the visual generator rather than sourcing the citing authors’ assessment of detection methods. The Introduction identifies Wav2Lip as the paper’s lip-synchronization network for generating talking-face videos; SV2TTS has a separate citation. (LLM, conf=0.90)
- Partly supportedcites [27] [27] Ye Jia, Yu Zhang, Ron J. Weiss, Quan Wang, Jonathan Shen, Fei Ren, Zhifeng Chen, Patrick Nguyen, Ruoming Pang, Ignacio Lopez Moreno, and Yonghui Wu. 2018. Transfer learning from speaker verification to multispeaker text-tospeech synthesis. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS'18) . Curran Associates Inc., Red Hook, NY, USA, 4485-4495. - sourceExperimental — accuracy not yet measured
The Conclusion (p. 9) describes the cited work's multispeaker text-to-speech system and says its output does not attain human-level naturalness. It does not assess audio generated for LAV-DF or whether its quality is insufficient for state-of-the-art detection methods. (LLM, conf=0.84)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
- Supported
32 more claims
Create a free account to see all 66 claims and to verify the 12 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 14
- Borderline: one of the tests for a substantial claim is unclear. 1
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“there are currently only two datasets [3, 7] specifically designed for the TFL task, both of which are English-centric.”
From CLFormer: a cross-lingual transformer framework for temporal forgery localization (2025) · cites this paper as [7]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“AV-Deepfake1M and its follow-on challenge infrastructure target large-scale audio-visual detection and localization [42]”
From A Review of Tools and Technologies to Combat Deepfakes (2026) · cites this paper as [42]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“MMMS-BA has obtained better performance on the AV-Deepfake1M dataset when compared to the best model in [8].”
From Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization (2024) · cites this paper as [8]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For the AVDeepfake1M dataset, training and validation sets are available, and the testing set has not yet been released.”
From Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization (2024) · cites this paper as [8]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The latest forgery techniques exploit multi-modal dependencies, including synchronizing fake speech with lip movements [5], manipulating both video and textual descriptions [6], and simultaneously altering audio-visual content [7].”
From Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges (2024) · cites this paper as [7]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“| Validation | | 14,235 | 43,105 | 54,730 |”
Reported 54730 · recomputed 57340
Citations
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · cited 1×
“The user study results presented in Table 5 indicate that the deepfake content in AV-Deepfake1M is very challenging to detect for humans.”
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
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 2×
“Here we provide further details on the user study (see Section 3.3) that aims to evaluate humans’ performance in detecting the highly realistic deepfake content in AV-Deepfake1M.”
InfluentialAdvances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Multiscale structural similarity for image quality assessment
Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2004) · The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 · doi:10.1109/acssc.2003.1292216 · Cited by 6,253
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
FaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 3×
“The reported performance is based on different subsets, described in Section 4.1, and different levels of label access during training, described in Section 4.2.”
InfluentialVoxCeleb2: Deep Speaker Recognition
Chung, J. S., Nagrani, A., & Zisserman, A. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1929 · Cited by 2,256 · cited 1×
“We utilize ChatGPT for altering the real transcripts.”
Research works printed but not linked: 5
- Songwei Ge, Thomas Hayes, Harry Yang, Xi Yin, Guan Pang, David Jacobs, Jia-Bin Huang, and Devi Parikh. 2022. Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer. In Proceedings of the European Conference on Computer Vision (ECCV) (Lecture Notes in Computer Science), Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner (Eds.). Springer Nature Switzerland, Cham, 102--118.
- 10.5555/3327345.3327360 · doi:10.5555/3327345.3327360
- Yuezun Li and Siwei Lyu. 2019. Exposing DeepFake Videos By Detecting Face Warping Artifacts. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 7.
- 10.5555/3618408.3619590 · doi:10.5555/3618408.3619590
- Yang Yu, Xiaolong Liu, Rongrong Ni, Siyuan Yang, Yao Zhao, and Alex C. Kot. 2023. PVASS-MDD: Predictive Visual-audio Alignment Self-supervision for Multimodal Deepfake Detection. IEEE Transactions on Circuits and Systems for Video Technology (2023), 1--1.
Cited by
Deepfake: definitions, performance metrics and standards, datasets, and a meta-review
Altuncu, E., Franqueira, V. N. L., & Li, S. (2024) · Frontiers in Big Data · doi:10.3389/fdata.2024.1400024 · Cited by 134
MLAAD: The Multi-Language Audio Anti-Spoofing Dataset
Müller, N. M., Kawa, P., Choong, W. H., Casanova, E., Gölge, E., Müller, T., Syga, P., Sperl, P., & Böttinger, K. (2024) · 2024 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650962 · Cited by 73
Enhancing multimodal deepfake detection with local–global feature integration and diffusion models
Javed, M., Zhang, Z., Dahri, F. H., & Kumar, T. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-03970-7 · Cited by 78
“The evaluation used the following datasets: • FakeAVCeleb A multimodal dataset with balanced demo-graphics and diverse manipulations [11].”
Audio–Visual Synchronization and Lip Movement Analysis for Real-Time Deepfake Detection
Javed, M., Zhang, Z., Dahri, F. H., Laghari, A. A., Krajčík, M., & Almadhor, A. S. (2025) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-025-00911-7 · Cited by 62
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
Metadata
- Authors
- Cai, Z., Ghosh, S., Adatia, A. P., Hayat, M., Dhall, A., Gedeon, T., & Stefanov, K.
- Affiliations
- Monash University (AU)
- Curtin University (AU)
- Indian Institute of Technology Ropar (IN)
- Qualcomm (United States) (US)
- Flinders University (AU)
- ORCID
- Venue
- Proceedings of the 32nd ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2024-10-28
- Pages
- 7414-7423
- OpenAlex
- W4403791323
- Cited by
- 59
- References
- 50
- Citations by year
- 2026: 28 · 2025: 27 · 2024: 4
- FWCI
- 12.22
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM International Conference on Multimedia (ACM MM) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- Monash University Research Portal (Monash University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- 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, video manipulation, sound manipulation, synthetic dataset, large-scale datasets, data generation pipeline
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
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: AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset. https://app.cochat.ai/papers/10.1145/3664647.3680795
- The paper
- Cai, Z., Ghosh, S., Adatia, A. P., Hayat, M., Dhall, A., Gedeon, T., & Stefanov, K. (2024). AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset. Proceedings of the 32nd ACM International Conference on Multimedia. https://doi.org/10.1145/3664647.3680795
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.