# Safer Prompts: Reducing Risks from Memorization in Visual Generative AI

arXiv: https://arxiv.org/abs/2505.03338 · HTML: https://mlsanity.com/paper/2505.03338/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 7 of 7)

- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [Design Guidelines for Prompt Engineering Text-to-Image Generative Models](https://mlsanity.com/paper/2109.06977/) (2021)
- [Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2402.05375/) (2024)
- [Fantastic Copyrighted Beasts and How (Not) to Generate Them](https://mlsanity.com/paper/2406.14526/) (2024)
- [Evaluating and Mitigating IP Infringement in Visual Generative AI](https://mlsanity.com/paper/2406.04662/) (2024)

## Built on by (most cited first, 1 of 1)

- [Copyright Infringement Risk Reduction via Chain-of-Thought and Task Instruction Prompting](https://mlsanity.com/paper/2512.15442/) (2025)

## Abstract (arXiv)

Visual Generative AI models have demonstrated remarkable capability in generating high-quality images from user inputs like text prompts. However, because these models have billions of parameters, they risk memorizing certain parts of the training data and reproducing the memorized content. Memorization often raises concerns about safety of such models -- usually involving intellectual property (IP) infringement risk -- and deters their large scale adoption. In this paper, we evaluate the effectiveness of prompt engineering techniques in reducing memorization risk in image generation. Our findings demonstrate the effectiveness of prompt engineering in reducing the similarity between generated images and the training data of diffusion models, while maintaining relevance and aestheticity of the generated output.