mlsanityData to 7 Oct 2026

Deepfake CAPTCHA: A Method for Preventing Fake Calls

arXiv 2301.03064 ↗First posted 8 Jan 2023cs.CR cs.CV cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Deep learning technology has made it possible to generate realistic content of specific individuals. These `deepfakes' can now be generated in real-time which enables attackers to impersonate people over audio and video calls. Moreover, some methods only need a few images or seconds of audio to steal an identity. Existing defenses perform passive analysis to detect fake content. However, with the rapid progress of deepfake quality, this may be a losing game. In this paper, we propose D-CAPTCHA: an active defense against real-time deepfakes. The approach is to force the adversary into the spotlight by challenging the deepfake model to generate content which exceeds its capabilities. By doing so, passive detection becomes easier since the content will be distorted. In contrast to existing CAPTCHAs, we challenge the AI's ability to create content as opposed to its ability to classify content. In this work we focus on real-time audio deepfakes and present preliminary results on video. In our evaluation we found that D-CAPTCHA outperforms state-of-the-art audio deepfake detectors with an accuracy of 91-100% depending on the challenge (compared to 71% without challenges). We also performed a study on 41 volunteers to understand how threatening current real-time deepfake attacks are. We found that the majority of the volunteers could not tell the difference between real and fake audio.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 31 of its 88 references that are in the map. First posted on arXiv 8 Jan 2023.

Builds on

31 of 88 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2020First Order Motion Model for Image Animationcited by 698
  4. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  5. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 280
  6. 2020The Creation and Detection of Deepfakes: A Surveycited by 246
  7. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 173
  8. 2020End-to-end anti-spoofing with RawNet2cited by 160
  9. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 157
  10. 2022MegaPortraits: One-shot Megapixel Neural Head Avatarscited by 131
  11. 2019One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalizationcited by 82
  12. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
19 more
  1. 2020Evading Deepfake-Image Detectors with White- and Black-Box Attackscited by 80
  2. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 68
  3. 2020One-class Learning Towards Synthetic Voice Spoofing Detectioncited by 59
  4. 2021StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversioncited by 57
  5. 2020FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attentioncited by 37
  6. 2020F0-consistent many-to-many non-parallel voice conversion via conditional autoencodercited by 35
  7. 2019Deep Residual Neural Networks for Audio Spoofing Detectioncited by 33
  8. 2021Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectorscited by 32
  9. 2020CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversioncited by 25
  10. 2019ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworkscited by 23
  11. 2021Raw Differentiable Architecture Search for Speech Deepfake and Spoofing Detectioncited by 22
  12. 2021Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniquescited by 11
  13. 2022Deepfake audio detection by speaker verificationcited by 11
  14. 2022Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detectioncited by 9
  15. 2022SpecRNet: Towards Faster and More Accessible Audio DeepFake Detectioncited by 9
  16. 2021MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium featurescited by 8
  17. 2020ConVoice: Real-Time Zero-Shot Voice Style Transfer with Convolutional Networkcited by 6
  18. 2022Frequency Domain-Based Detection of Generated Audiocited by 3
  19. 2020A Cross-Verification Approach for Protecting World Leaders from Fake and Tampered Audiocited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 1; 2026: 1.

7 papers.

  1. 2024Are You Human? An Adversarial Benchmark to Expose LLMscited by 5
  2. 2023Discussion Paper: The Threat of Real Time Deepfakescited by 4
  3. 2024Passive Deepfake Detection Across Multi-modalities: A Comprehensive Surveycited by 4
  4. 2023SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANscited by 3
  5. 2025Aura-CAPTCHA: A Reinforcement Learning and GAN-Enhanced Multi-Modal CAPTCHA Systemcited by 3
  6. 2024D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attackcited by 1
  7. 2026Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attackscited by 0