# Deepfake CAPTCHA: A Method for Preventing Fake Calls

arXiv: https://arxiv.org/abs/2301.03064 · HTML: https://mlsanity.com/paper/2301.03064/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 88 references that are in the map.
- First posted on arXiv 8 Jan 2023.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection](https://mlsanity.com/paper/1904.05441/) (2019)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection](https://mlsanity.com/paper/2109.00537/) (2021)
- [MegaPortraits: One-shot Megapixel Neural Head Avatars](https://mlsanity.com/paper/2207.07621/) (2022)
- [One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization](https://mlsanity.com/paper/1904.05742/) (2019)
- [Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward](https://mlsanity.com/paper/2103.00484/) (2021)
- [Evading Deepfake-Image Detectors with White- and Black-Box Attacks](https://mlsanity.com/paper/2004.00622/) (2020)
- [End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection](https://mlsanity.com/paper/2107.12710/) (2021)
- [One-class Learning Towards Synthetic Voice Spoofing Detection](https://mlsanity.com/paper/2010.13995/) (2020)
- [StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion](https://mlsanity.com/paper/2107.10394/) (2021)
- [FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention](https://mlsanity.com/paper/2010.14150/) (2020)
- [F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder](https://mlsanity.com/paper/2004.07370/) (2020)
- [Deep Residual Neural Networks for Audio Spoofing Detection](https://mlsanity.com/paper/1907.00501/) (2019)
- [Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors](https://mlsanity.com/paper/2109.02993/) (2021)
- [CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion](https://mlsanity.com/paper/2010.11672/) (2020)
- [ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks](https://mlsanity.com/paper/1904.01120/) (2019)
- [Raw Differentiable Architecture Search for Speech Deepfake and Spoofing Detection](https://mlsanity.com/paper/2107.12212/) (2021)
- [Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques](https://mlsanity.com/paper/2104.00931/) (2021)
- [Deepfake audio detection by speaker verification](https://mlsanity.com/paper/2209.14098/) (2022)
- [Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection](https://mlsanity.com/paper/2206.13979/) (2022)
- [SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection](https://mlsanity.com/paper/2210.06105/) (2022)
- [MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features](https://mlsanity.com/paper/2110.02500/) (2021)
- [ConVoice: Real-Time Zero-Shot Voice Style Transfer with Convolutional Network](https://mlsanity.com/paper/2005.07815/) (2020)
- [Frequency Domain-Based Detection of Generated Audio](https://mlsanity.com/paper/2205.01806/) (2022)

## Built on by (most cited first, 7 of 7)

- [Are You Human? An Adversarial Benchmark to Expose LLMs](https://mlsanity.com/paper/2410.09569/) (2024)
- [Discussion Paper: The Threat of Real Time Deepfakes](https://mlsanity.com/paper/2306.02487/) (2023)
- [Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey](https://mlsanity.com/paper/2411.17911/) (2024)
- [SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs](https://mlsanity.com/paper/2307.09435/) (2023)
- [Aura-CAPTCHA: A Reinforcement Learning and GAN-Enhanced Multi-Modal CAPTCHA System](https://mlsanity.com/paper/2508.14976/) (2025)
- [D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack](https://mlsanity.com/paper/2409.07390/) (2024)
- [Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks](https://mlsanity.com/paper/2609.11404/) (2026)

## 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.