Search icon
ReadWrite
see notifications
Notifications
see more
    paint-brush
    What Happens When AI Tries to Mimic Protected Art? by@torts

    What Happens When AI Tries to Mimic Protected Art?

    by TortsDecember 12th, 2024
    Read on Terminal Reader
    Read this story w/o Javascript
    tldt arrow

    Too Long; Didn't Read

    This section illustrates the impact of robust mimicry methods on protected artwork, showing visual comparisons for each method from Gaussian Noising to Noisy Upscaling.
    featured image - What Happens When AI Tries to Mimic Protected Art?
    Torts HackerNoon profile picture

    Abstract and 1. Introduction

    1. Background and Related Work

    2. Threat Model

    3. Robust Style Mimicry

    4. Experimental Setup

    5. Results

      6.1 Main Findings: All Protections are Easily Circumvented

      6.2 Analysis

    6. Discussion and Broader Impact, Acknowledgements, and References

    A. Detailed Art Examples

    B. Robust Mimicry Generations

    C. Detailed Results

    D. Differences with Glaze Finetuning

    E. Findings on Glaze 2.0

    F. Findings on Mist v2

    G. Methods for Style Mimicry

    H. Existing Style Mimicry Protections

    I. Robust Mimicry Methods

    J. Experimental Setup

    K. User Study

    L. Compute Resources

    B Robust Mimicry Generations

    Figure 11: Style mimicry for all protections using naive mimicry—no robust method is used and we finetune directly on protected images. We randomly chose artists and prompts. Each image pair shows the protected generation and generation from unprotected art.


    Figure 12: Style mimicry for all protections using Gaussian Noising. We randomly chose artists and prompts. Each image pair shows the protected robust generation and generation from unprotected art.


    Figure 13: Style mimicry for all protections using DiffPure. We randomly chose artists and prompts. Each image pair shows the protected robust generation and generation from unprotected art.


    Figure 14: Style mimicry for all protections using IMPRESS++. We randomly chose artists and prompts. Each image pair shows the protected robust generation and generation from unprotected art.


    Figure 15: Style mimicry for all protections using Noisy Upscaling. We randomly chose artists and prompts. Each image pair shows the protected robust generation and generation from unprotected art.


    Authors:

    (1) Robert Honig, ETH Zurich ([email protected]);

    (2) Javier Rando, ETH Zurich ([email protected]);

    (3) Nicholas Carlini, Google DeepMind;

    (4) Florian Tramer, ETH Zurich ([email protected]).

    This paper is available on arxiv under CC BY 4.0 license.


    HackerNoon Newsletter
    L O A D I N G
    . . . comments & more!

    About Author

    Torts HackerNoon profile picture
    Torts@torts
    Exploring the legal landscape of the digital age. Read my articles to understand the why behind the what.
    Read my storiesAbout @torts

    TOPICS

    purcat-imgtech-stories #ai-forgery #generative-ai #ai-style-mimicry #image-theft-by-ai #protecting-art-from-ai #glaze-protection-tool #black-box-ai-access #robust-mimicry-methods

    THIS ARTICLE WAS FEATURED IN...

    Permanent on Arweave
    Read on Terminal Reader Terminal
    Read this story w/o Javascript Lite
    Also published here
    Hackernoon
    Threads
    Bsky

    RELATED STORIES

    Article Thumbnail
    Why AI Style Protections Fall Short Against Advanced Mimicry Techniques
    by torts
    Dec 10, 2024
    #ai-forgery
    Article Thumbnail
    New Research Reveals Vulnerabilities in Popular Art Protection Tools Against AI Theft
    by escholar
    Dec 10, 2024
    #ai-forgery
    Article Thumbnail
    Why AI Style Protections Fall Short Against Advanced Mimicry Techniques
    by torts
    Dec 10, 2024
    #ai-forgery
    Article Thumbnail
    How AI Forgers Bypass Style Protections to Mimic Artists' Work
    by torts
    Dec 10, 2024
    #ai-forgery
    Article Thumbnail
    New Study Shows AI Can Now Mimic Art Styles More Accurately Than Ever
    by torts
    Dec 10, 2024
    #ai-forgery
    Join HackerNoonloading
    Latest technology trends. Customized Experience. Curated Stories. Publish Your Ideas