mlsanityData to 7 Oct 2026

A Representative Study on Human Detection of Artificially Generated Media Across Countries

arXiv 2312.05976 ↗First posted 10 Dec 2023cs.CR cs.AI cs.CYcited by 22

Not on the map. Why?

Abstract (arXiv)

AI-generated media has become a threat to our digital society as we know it. These forgeries can be created automatically and on a large scale based on publicly available technology. Recognizing this challenge, academics and practitioners have proposed a multitude of automatic detection strategies to detect such artificial media. However, in contrast to these technical advances, the human perception of generated media has not been thoroughly studied yet. In this paper, we aim at closing this research gap. We perform the first comprehensive survey into people's ability to detect generated media, spanning three countries (USA, Germany, and China) with 3,002 participants across audio, image, and text media. Our results indicate that state-of-the-art forgeries are almost indistinguishable from "real" media, with the majority of participants simply guessing when asked to rate them as human- or machine-generated. In addition, AI-generated media receive is voted more human like across all media types and all countries. To further understand which factors influence people's ability to detect generated media, we include personal variables, chosen based on a literature review in the domains of deepfake and fake news research. In a regression analysis, we found that generalized trust, cognitive reflection, and self-reported familiarity with deepfakes significantly influence participant's decision across all media categories.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 50 of its 130 references that are in the map. First posted on arXiv 10 Dec 2023.

Builds on

50 of 130 references.

References · 50

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2022Generative Adversarial Networkscited by 5,603
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  10. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  11. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
38 more
  1. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  2. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  10. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  11. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  12. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  13. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  14. 2017Wasserstein GANcited by 635
  15. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  16. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  17. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  18. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  19. 2020How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Modelscited by 313
  20. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  21. 2018Adversarial Audio Synthesiscited by 222
  22. 2018Do GANs leave artificial fingerprints?cited by 188
  23. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  24. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  25. 2015Practical Bayesian model evaluation using leave-one-out cross-validation and WAICcited by 110
  26. 2017Structured Attention Networkscited by 95
  27. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90
  28. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  29. 2018Detecting GAN-generated Imagery using Color Cuescited by 75
  30. 2019Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloningcited by 66
  31. 2017On the regularization of Wasserstein GANscited by 65
  32. 2022Deepfake Text Detection: Limitations and Opportunitiescited by 37
  33. 2020Detecting CNN-Generated Facial Images in Real-World Scenarioscited by 32
  34. 2021More Real than Real: A Study on Human Visual Perception of Synthetic Facescited by 23
  35. 2022Human Detection of Political Speech Deepfakes across Transcripts, Audio, and Videocited by 16
  36. 2021Human Perception of Audio Deepfakescited by 15
  37. 2021HUI-Audio-Corpus-German: A high quality TTS datasetcited by 14
  38. 2022You Can Have Your Data and Balance It Too: Towards Balanced and Efficient Multilingual Modelscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 9; 2026: 7.

22 papers.

Sort:

By area:

  1. 2025Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024cited by 40
  2. 2024On the Challenges and Opportunities in Generative AIcited by 31
  3. 2024Organic or Diffused: Can We Distinguish Human Art from AI-generated Images?cited by 21
  4. 2024AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Imagescited by 10
  5. 2024Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakescited by 7
  6. 2025Adoption of Watermarking for Generative AI Systems in Practice and Implications under the new EU AI Actcited by 7
  7. 2024Adversarial Robustness of AI-Generated Image Detectors in the Real Worldcited by 6
  8. 2024The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methodscited by 4
  9. 2025RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectorscited by 4
  10. 2025Gen-Review: A Large-scale Dataset of AI-Generated (and Human-written) Peer Reviewscited by 3
  11. 2025Humans can learn to detect AI-generated texts, or at least learn when they can'tcited by 2
  12. 2025"That's another doom I haven't thought about": A User Study on AI Labels as a Safeguard Against Image-Based Misinformationcited by 2
10 more
  1. 2025Designing Effective Digital Literacy Interventions for Boosting Deepfake Discernmentcited by 1
  2. 2025PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Imagescited by 1
  3. 2026Human-AI Ensembles Improve Deepfake Detection in Low-to-Medium Quality Videoscited by 1
  4. 2026DeGenTWeb: A First Look at LLM-dominant Websitescited by 1
  5. 2026The Future of Facts: Tracing the Factual Generation-Verification Gapcited by 1
  6. 2026BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectorscited by 1
  7. 2025Generative Propagandacited by 0
  8. 2026Show, Don't TELL: Explainable AI-Generated Text Detectioncited by 0
  9. 2026Can You Trust What You See? Human and AI Detection of Synthetic Legal Evidencecited by 0
  10. 2026Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibrationcited by 0