What Happens When AI Tries to Mimic Protected Art?

What Happens When AI Tries to Mimic Protected Art?


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.

\

:::info
Authors:

(1) Robert Honig, ETH Zurich (robert.hoenig@inf.ethz.ch);

(2) Javier Rando, ETH Zurich (javier.rando@inf.ethz.ch);

(3) Nicholas Carlini, Google DeepMind;

(4) Florian Tramer, ETH Zurich (florian.tramer@inf.ethz.ch).

:::


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

:::

\



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *