paper-with-me

Papers

Prompt Stealing Attacks Against Text-to-Image Generation Models

2023-02-20 · Xinyue Shen, Yiting Qu, Michael Backes, Yang Zhang

Text-to-Image generation models have revolutionized the artwork design process and enabled anyone to create high-quality images by entering text descriptions called prompts. Creating a high-quality prompt that consists of a subject and several modifiers can be time-consuming and costly. In consequence, a trend of trading high-quality prompts on specialized marketplaces has emerged. In this paper, we perform the first study on understanding the threat of a novel attack, namely prompt stealing attack, which aims to steal prompts from generated images by text-to-image generation models. Successful prompt stealing attacks directly violate the intellectual property of prompt engineers and jeopardize the business model of prompt marketplaces. We first perform a systematic analysis on a dataset collected by ourselves and show that a successful prompt stealing attack should consider a prompt's subject as well as its modifiers. Based on this observation, we propose a simple yet effective prompt stealing attack, PromptStealer. It consists of two modules: a subject generator trained to infer the subject and a modifier detector for identifying the modifiers within the generated image. Experimental results demonstrate that PromptStealer is superior over three baseline methods, both quantitatively and qualitatively. We also make some initial attempts to defend PromptStealer. In general, our study uncovers a new attack vector within the ecosystem established by the popular text-to-image generation models. We hope our results can contribute to understanding and mitigating this emerging threat.

📄 PDF Abstract BibTeX arXiv:2302.09923

Code (1)

verazuo/prompt-stealing-attack 공식 구현 pytorch

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Similar Papers 제목 키워드 기반

Prompt Stealing Attacks Against Large Language Models

2024-02-20 · Zeyang Sha, Yang Zhang

The increasing reliance on large language models (LLMs) such as ChatGPT in various fields emphasizes the importance of ``prompt engineering,'' a technology to improve the quality of model outputs. With companies investin…

Prompt Engineering

Large Language Models for Link Stealing Attacks Against Graph Neural Networks

2024-06-22 · Faqian Guan, Tianqing Zhu, Hui Sun, Wanlei Zhou 외

Graph data contains rich node features and unique edge information, which have been applied across various domains, such as citation networks or recommendation systems. Graph Neural Networks (GNNs) are specialized for ha…

Recommendation Systems

Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders

2022-01-19 · CVPR 2023 1 · Zeyang Sha, Xinlei He, Ning Yu, Michael Backes 외

Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images. They encode images into rich features that are oblivious to downstream tasks. Behind their revolutiona…

Contrastive LearningRepresentation Learning

Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts

2025-09-11 · Felix Mächtle, Ashwath Shetty, Jonas Sander, Nils Loose 외 arxiv

Diffusion models have significantly advanced text-to-image generation, enabling the creation of highly realistic images conditioned on textual prompts and seeds. Given the considerable intellectual and economic value emb…

Text-to-Image Generation

Model Stealing Attacks Against Inductive Graph Neural Networks

2021-12-15 · Yun Shen, Xinlei He, Yufei Han, Yang Zhang

Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, …

model