Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts
Open Access
- 4 June 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 422-438
Abstract
No abstract availableAll Related Versions
Funding Information
- This work was supported by the German Federal Ministry of Research, Technology and Space (BMFTR) through the projects SAM Smart and AnoMed. (SAM Smart & AnoMed)
This publication has 9 references indexed in Scilit:
- Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models2025
- Reverse Stable Diffusion: What prompt was used to generate this image?Computer Vision and Image Understanding, 2024
- Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models2024
- Madvex: Instrumentation-Based Adversarial Attacks on Machine Learning Malware Detection2023
- Monte Carlo and Reconstruction Membership Inference Attacks against Generative ModelsProceedings on Privacy Enhancing Technologies, 2019
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- ChaCha20 and Poly1305 for IETF Protocols2015
- Practical Nonparametric StatisticsTechnometrics, 2000
- Conditioning of quasi-Newton methods for function minimizationMathematics of Computation, 1970