用思维链和任务指令提示降低图像生成的版权风险
Copyright Infringement Risk Reduction via Chain-of-Thought and Task Instruction Prompting
- 结合思维链与任务指令，减少对训练数据的直接复现
- 实验显示该方法在多种模型上显著降低版权内容生成率
- 适合关注AI法律合规性的开发者与企业用户
大规模文本到图像生成模型可能记忆并再现其训练数据，而训练数据常包含受版权保护的内容，导致生成结果存在侵权风险，可能给AI使用者和开发者带来法律与财务损失。本文探索了思维链（chain-of-thought）与任务指令提示在降低版权内容生成方面的潜力。为此，提出一种整合这两种技术与其他两种版权缓解策略（负向提示、提示重写）的方法。通过分析生成图像与受版权保护图像的相似度以及与用户输入的相关性，对多种模型进行了数值实验，揭示了不同模型复杂度下各技术的有效性。
原文摘要 · Abstract (English)
Large scale text-to-image generation models can memorize and reproduce their training dataset. Since the training dataset often contains copyrighted material, reproduction of training dataset poses a copyright infringement risk, which could result in legal liabilities and financial losses for both the AI user and the developer. The current works explores the potential of chain-of-thought and task instruction prompting in reducing copyrighted content generation. To this end, we present a formulation that combines these two techniques with two other copyright mitigation strategies: a) negative prompting, and b) prompt re-writing. We study the generated images in terms their similarity to a copyrighted image and their relevance of the user input. We present numerical experiments on a variety of models and provide insights on the effectiveness of the aforementioned techniques for varying model complexity.
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。