[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to main content
Springer Nature Link
Log in

The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking

  • Conference paper
  • First Online:
Computer Security – ESORICS 2024 (ESORICS 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14982))

Included in the following conference series:

  • 722 Accesses

Abstract

Generative AI models can produce high-quality images based on text prompts. The generated images often appear indistinguishable from images generated by conventional optical photography devices or created by human artists (i.e., real images). While the outstanding performance of such generative models is generally well received, security concerns arise. For instance, such image generators could be used to facilitate fraud or scam schemes, generate and spread misinformation, or produce fabricated artworks. In this paper, we present a systematic attempt at understanding and detecting AI-generated images (AI-art) in adversarial scenarios. First, we collect and share a dataset of real images and their corresponding artificial counterparts generated by four popular AI image generators. The dataset, named ARIA, contains over 140K images in five categories: artworks (painting), social media images, news photos, disaster scenes, and anime pictures. This dataset can be used as a foundation to support future research on adversarial AI-art. Next, we present a user study that employs the ARIA dataset to evaluate if real-world users can distinguish with or without reference images. In a benchmarking study, we further evaluate if state-of-the-art open-source and commercial AI image detectors can effectively identify the images in the ARIA dataset. Finally, we present a ResNet-50 classifier and evaluate its accuracy and transferability on the ARIA dataset. The ARIA dataset and the project source code are shared at: https://github.com/AdvAIArtProject/AdvAIArt.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
GBP 19.95
Price includes VAT (United Kingdom)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
GBP 49.99
Price includes VAT (United Kingdom)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
GBP 59.99
Price includes VAT (United Kingdom)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. 10 midjourney statistics demonstrating why its better than other AI art generators. Skim AI (2024)

    Google Scholar 

  2. Risk in focus: Generative A.I. and the 2024 election cycle. CISA (2024)

    Google Scholar 

  3. Agarwal, A., Singh, R., Vatsa, M., Noore, A.: Swapped! digital face presentation attack detection via weighted local magnitude pattern. In: IEEE IJCB (2017)

    Google Scholar 

  4. Akhtar, Z., Dasgupta, D.: A comparative evaluation of local feature descriptors for deepfakes detection. In: IEEE HST (2019)

    Google Scholar 

  5. billywzh717: N24news. https://github.com/billywzh717/N24News (2022)

  6. Bird, J.J., Lotfi, A.: CIFAKE: image classification and explainable identification of AI-generated synthetic images. IEEE Access 12, 15642–15650 (2024)

    Article  Google Scholar 

  7. Bray, S.D., Johnson, S.D., Kleinberg, B.: Testing human ability to detect ‘deepfake’ images of human faces. J. Cybersecur. 9(1), tyad011 (2023)

    Google Scholar 

  8. Chan, K., Swenson, A.: One Tech Tip: How to Spot AI-Generated Deepfake Images. The Associated Press, New York (2024)

    Google Scholar 

  9. Chen, M., Tworek, J., et al.: Evaluating large language models trained on code. arXiv:2107.03374 (2021)

  10. Cho, W.: AI companies take hit as judge says artists have ‘public interest’ in pursuing lawsuits. ARTnews (2024)

    Google Scholar 

  11. Croitoru, F.A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: a survey. In: IEEE TPAMI (2023)

    Google Scholar 

  12. Data, E.D.I.: Case 1739 AI-generated image showing accident between GMC hummer EV and tesla cybertruck has gone viral with false claims. D-Intent Data (2024)

    Google Scholar 

  13. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, IEEE (2009)

    Google Scholar 

  14. Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)

    Google Scholar 

  15. Draganovic, A., Dambra, S., Iuit, J.A., Roundy, K., Apruzzese, G.: “Do users fall for real adversarial phishing?” investigating the human response to evasive webpages. In: APWG eCrime (2023)

    Google Scholar 

  16. Duffy, C.: Top AI photo generators produce misleading election-related images, study finds. In: CNN (2024)

    Google Scholar 

  17. Edwards, B.: Flooded with AI-generated images, some art communities ban them completely. In: arstechnica (2022)

    Google Scholar 

  18. Epstein, Z., Levine, S., Rand, D.G., Rahwan, I.: Who gets credit for AI-generated art? Iscience 23(9), 101515 (2020)

    Google Scholar 

  19. Evan, S.: Pixiv top daily illustration 2018. Kaggle. https://www.kaggle.com/datasets/stevenevan99/pixiv-top-daily-illustration-2018 (2019)

  20. Fake image detector: fake image detector. https://www.fakeimagedetector.com/contact-us/ (2024)

  21. Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)

    Google Scholar 

  22. Gragnaniello, D., Cozzolino, D., Marra, F., Poggi, G., Verdoliva, L.: Are GAN generated images easy to detect? a critical analysis of the state-of-the-art. In: IEEE ICME (2021)

    Google Scholar 

  23. Ha, A.Y.J., et al.: Organic or diffused: can we distinguish human art from AI-generated images? arXiv:2402.03214 (2024)

  24. Hassan Hicham ElNahrawy: AI or not. https://huggingface.co/Nahrawy/AIorNot/ (2023)

  25. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  26. He, Y., Yu, N., Keuper, M., Fritz, M.: Beyond the spectrum: Detecting deepfakes via re-synthesis. arXiv:2105.14376 (2021)

  27. Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)

    Google Scholar 

  28. Hong, Y., Zhang, J.: Wildfake: a large-scale challenging dataset for AI-generated images detection. arXiv:2402.11843 (2024)

  29. Icaro: Best artworks of all time. Kaggle. https://www.kaggle.com/datasets/ikarus777/best-artworks-of-all-time (2023)

  30. isitai.com: Is it AI? https://isitai.com/ (2024)

  31. Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR (2018)

    Google Scholar 

  32. Katatikarn, J.: AI art statistics: the ultimate list in 2024. In: Academy Of Animated Art (2024)

    Google Scholar 

  33. Kavafian, H.: How to identify AI-generated images (2023)

    Google Scholar 

  34. KI-Tech Hertig: Illuminarty. https://illuminarty.ai/ (2024)

  35. Korshunov, P., Marcel, S.: Deepfakes: a new threat to face recognition? assessment and detection. arXiv:1812.08685 (2018)

  36. koushikvikram: Multimodal image retrieval. Github. https://github.com/koushikvikram/multimodal-image-retrieval (2021)

  37. Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)

    Google Scholar 

  38. Lei, J., Tang, J., Jia, K.: Rgbd2: Generative scene synthesis via incremental view inpainting using RGBD diffusion models. In: CVPR (2023)

    Google Scholar 

  39. Li, Y., Lyu, S.: Exposing deepfake videos by detecting face warping artifacts. arXiv:1811.00656 (2018)

  40. Li, Y., Yang, X., Sun, P., Qi, H., Lyu, S.: Celeb-DF: a large-scale challenging dataset for deepfake forensics. In: CVPR (2020)

    Google Scholar 

  41. Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)

    Google Scholar 

  42. Liu, Z., Yao, Z., Li, F., Luo, B.: On the detectability of chatgpt content: benchmarking, methodology, and evaluation through the lens of academic writing. arXiv:2306.05524 (2023)

  43. Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR (2022)

    Google Scholar 

  44. Lu, Z., et al.: Seeing is not always believing: Benchmarking human and model perception of AI-generated images. In: NeurIPS (2024)

    Google Scholar 

  45. Matthew Maybe: Ai image detector. https://huggingface.co/umm-maybe/AI-image-detector/ (2022)

  46. Matusevski, A.: Instagram images - 1,211,625 posts. Kaggle. https://www.kaggle.com/datasets/shmalex/instagram-images (2022)

  47. Midjourney: Can i use my images commercially? MidJourney. https://help.midjourney.com/en/articles/8150363-can-i-use-my-images-commercially (2024)

  48. Midjourney: Midjourney home. https://www.midjourney.com/home (2024)

  49. Mirza, R.: How AI deepfakes threaten the 2024 elections. J. Resour. (2023)

    Google Scholar 

  50. Mo, H., Chen, B., Luo, W.: Fake faces identification via convolutional neural network. In: ACM workshop on information hiding and multimedia security (2018)

    Google Scholar 

  51. Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML (2021)

    Google Scholar 

  52. Office, U.S.C.: Usco letter on AI and copyright initiative update (2024)

    Google Scholar 

  53. Ojha, U., Li, Y., Lee, Y.J.: Towards universal fake image detectors that generalize across generative models. In: CVPR (2023)

    Google Scholar 

  54. OpenAI: Can i sell images i create with dall\(\cdot \)e? OpenAI Documentation (2024)

    Google Scholar 

  55. OpenAI: Dall\(\cdot \)e: Creating images from text. https://openai.com/research/dall-e (2024)

  56. Organika.ai: Sdxl detector. https://huggingface.co/Organika/sdxl-detector/ (2024)

  57. Pashankar, S.: Scammers litter dating apps with AI-generated profile pics. Bloomberg (2024)

    Google Scholar 

  58. Rabiner, L., Juang, B.: An introduction to hidden markov models. IEEE ASSP Mag. 3(1), 4–16 (1986)

    Article  Google Scholar 

  59. Radford, A., Kim, J.W., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)

    Google Scholar 

  60. Rae, J.W., Borgeaud, S., et al.: Scaling language models: methods, analysis & insights from training gopher. arXiv:2112.11446 (2021)

  61. Rahman, M.A., Paul, B., Sarker, N.H., Hakim, Z.I.A., Fattah, S.A.: Artifact: a large-scale dataset with artificial and factual images for generalizable and robust synthetic image detection. In: IEEE ICIP (2023)

    Google Scholar 

  62. Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125 (2022)

  63. Reidy, M., Mallon, H., Luo, J.: Investigating the effectiveness of deep learning and CFA interpolation based classifiers on identifying AIGC. In: IEEE BigData (2023)

    Google Scholar 

  64. Reynolds, D.A., et al.: Gaussian mixture models. Encyclopedia Biometrics 741(659-663) (2009)

    Google Scholar 

  65. Roose, K.: An AI-generated picture won an art prize. artists aren’t happy (2022)

    Google Scholar 

  66. Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nießner, M.: Faceforensics++: learning to detect manipulated facial images. In: ICCV (2019)

    Google Scholar 

  67. Rudolf Kenechukwu Enyimba: Deepfake image detection (CNN). https://huggingface.co/spaces/Wvolf/CNN_Deepfake_Image_Detection/ (2024)

  68. Sganga, N.: Is that Facebook account real? meta reports ‘rapid rise’ in AI-generated profile pictures. CBS News (2022)

    Google Scholar 

  69. Sha, Z., Li, Z., Yu, N., Zhang, Y.: De-fake: detection and attribution of fake images generated by text-to-image generation models. In: ACM CCS (2023)

    Google Scholar 

  70. Sightengine: sightengine. https://sightengine.com/ (2024)

  71. Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)

    Google Scholar 

  72. Song, Y., Durkan, C., Murray, I., Ermon, S.: Maximum likelihood training of score-based diffusion models. In: NeurIPS (2021)

    Google Scholar 

  73. Song, Y., Ermon, S.: Improved techniques for training score-based generative models. In: NeurIPS (2020)

    Google Scholar 

  74. Stability AI Ltd: Dreamstudio. https://dreamstudio.com/about/ (2024)

  75. StarryAI: Starryai home. https://starryai.com/ (2024)

  76. Steele, C.: How to detect AI-generated images (2024)

    Google Scholar 

  77. Straub, J.: Using subject face brightness assessment to detect ‘deep fakes’ (conference presentation). In: Real-Time Image Processing and Deep Learning, vol. 10996, p. 109960H. SPIE (2019)

    Google Scholar 

  78. Telperion: Diasterdatasetraw. Kaggle. https://www.kaggle.com/datasets/telperion/diasterdatasetraw (2022)

  79. Thompson, S.A.: We asked A.I. to create the joker. it generated a copyrighted image. (2024)

    Google Scholar 

  80. Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)

    Google Scholar 

  81. Verma, P.: The rise of AI fake news is creating a ‘misinformation superspreader’. The Washington Post (2023)

    Google Scholar 

  82. Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: CNN-generated images are surprisingly easy to spot... for now. In: CVPR (2020)

    Google Scholar 

  83. Wang, Y., Huang, Z., Hong, X.: Benchmarking deepart detection. arXiv:2302.14475 (2023)

  84. Wang, Z., Shan, X., Zhang, X., Yang, J.: N24news: a new dataset for multimodal news classification. In: LREC (2022)

    Google Scholar 

  85. Wang, Z., et al.: Dire for diffusion-generated image detection. In: ICCV (2023)

    Google Scholar 

  86. Wang, Z., Montoya, E., Munechka, D., Yang, H., Hoover, B., Chau, P.: Diffusiondb: a large-scale prompt gallery dataset for text-to-image generative models. In: ACL (2023)

    Google Scholar 

  87. Wei, Y., Tyson, G.: Understanding the impact of AI generated content on social media: The pixiv case (2024)

    Google Scholar 

  88. Wendling, M.: Ai can be easily used to make fake election photos. In: BBC (2024)

    Google Scholar 

  89. Wong, C.: Ai-generated images and video are here: how could they shape research? Nature (2024)

    Google Scholar 

  90. Workado LLC: Content at scale. https://contentatscale.ai/ (2024)

  91. World Economic Forum: Global risks report 2024 (2024)

    Google Scholar 

  92. Writer, A.R.: 9 simple ways to detect AI images (with examples) in 2024 (2024)

    Google Scholar 

  93. Wu, J., Gan, W., Chen, Z., Wan, S., Lin, H.: Ai-generated content (AIGC): a survey. arXiv:2304.06632 (2023)

  94. Xi, Z., Huang, W., Wei, K., Luo, W., Zheng, P.: Ai-generated image detection using a cross-attention enhanced dual-stream network. In: APSIPA ASC (2023)

    Google Scholar 

  95. Yang, L., Zhang, Z., Song, Y., Hong, S., Xu, R., Zhao, Y., Zhang, W., Cui, B., Yang, M.H.: Diffusion models: a comprehensive survey of methods and applications. ACM Comput. Surv. 56(4), 1–39 (2023)

    Article  Google Scholar 

  96. Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: Lsun: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv:1506.03365 (2015)

  97. Yuan, Y., Hao, Q., Apruzzese, G., Conti, M., Wang, G.: Are adversarial phishing webpages a threat in reality? understanding the users’ perception of adversarial webpages. In: Web Conference (2024)

    Google Scholar 

  98. Zhang, Y., Zheng, L., Thing, V.L.: Automated face swapping and its detection. In: IEEE ICSIP (2017)

    Google Scholar 

  99. Zhu, M., et al.: Genimage: a million-scale benchmark for detecting AI-generated image. In: NeurIPS (2024)

    Google Scholar 

Download references

Acknowledgments

This paper was supported in part by US National Science Foundation (NSF) grants IIS-2014552, DGE-1565570, CNS-2204785, CNS-2205868, SCC-2238208 and the Ripple University Blockchain Research Initiative. We thank the anonymous reviewers for their valuable comments and suggestions.

Author information

Authors and Affiliations

  1. EECS/I2S The University of Kansas, Lawrence, KS, USA

    Yuying Li, Zeyan Liu, Junyi Zhao, Liangqin Ren, Fengjun Li & Bo Luo

  2. Department of Computer Science, University of Rochester, Rochester, NY, 14627, USA

    Jiebo Luo

Authors
  1. Yuying Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zeyan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Junyi Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Liangqin Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Fengjun Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jiebo Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Bo Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bo Luo .

Editor information

Editors and Affiliations

  1. Institut Polytechnique de Paris, Palaiseau, France

    Joaquin Garcia-Alfaro

  2. Bydgoszcz University of Science and Technology, Bydgoszcz, Poland

    Rafał Kozik

  3. Bydgoszcz University of Science and Technology, Bydgoszcz, Poland

    Michał Choraś

  4. Norwegian University of Science and Technology - NTNU, Gjøvik, Norway

    Sokratis Katsikas

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Li, Y. et al. (2024). The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking. In: Garcia-Alfaro, J., Kozik, R., Choraś, M., Katsikas, S. (eds) Computer Security – ESORICS 2024. ESORICS 2024. Lecture Notes in Computer Science, vol 14982. Springer, Cham. https://doi.org/10.1007/978-3-031-70879-4_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-70879-4_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-70878-7

  • Online ISBN: 978-3-031-70879-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation