paint-brush
Compute Resources for Style Mimicry Experimentsby@torts
New Story

Compute Resources for Style Mimicry Experiments

by TortsDecember 15th, 2024
Read on Terminal Reader
Read this story w/o Javascript
tldt arrow

Too Long; Didn't Read

This section outlines the compute resources used in our experiments, including execution times for generating images and the additional time required by IMPRESS++.
featured image - Compute Resources for Style Mimicry Experiments
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

L Compute Resources

Table 4 reports the compute resources for our experiments.


Table 4: Compute resources for our experiments. Execution time per image / (artist) reports the execution time of the method to compute a single image, or the combined execution time for all samples of an artist, if the method operates on all samples of an artist at once. † Google Cloud ‡ IMPRESS++ requires an additional 2 seconds per image generation.


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).


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