通过优化提示词降低视觉生成模型的记忆风险。
Safer Prompts: Reducing Risks from Memorization in Visual Generative AI
- 用提示词工程减少生成图像与训练数据的相似性。
- 在保持图像质量与相关性的前提下，有效降低记忆风险。
- 适合关注AI安全与版权合规的开发者和研究者。
视觉生成AI模型能根据用户输入（如文本提示）生成高质量图像。但由于参数量巨大，模型可能记忆训练数据中的部分内容并重现，引发知识产权侵权等安全问题，阻碍其大规模应用。本文评估了提示词工程在降低扩散模型生成图像与训练数据间记忆风险方面的效果。结果表明，该方法能在保持输出相关性与美学质量的同时，显著降低生成图像与训练数据的相似性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。