通过对抗性保护机制，精准擦除扩散模型中的不良概念，同时最小化对其他内容的影响。
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
- 识别并保护受参数变化影响最大的概念，实现稳定擦除。
- 在Stable Diffusion上验证，相比现有方法更有效消除有害内容。
- 适合需要安全可控生成的场景，如内容审核与合规生成。
扩散模型虽能从文本生成高质量图像，但因训练数据未加过滤，可能产生有害内容。现有方法试图在删除特定概念的同时保留中性内容或控制参数变化，但平衡难题仍存。本文提出识别并保护受参数扰动影响最显著的概念（即对抗性概念），以实现稳定擦除且对其他概念影响最小。我们在Stable Diffusion模型上验证该方法，结果表明其在去除不希望出现的内容方面优于当前最优技术，同时保持无关内容的完整性。代码已开源：https://github.com/tuananhbui89/Erasing-Adversarial-Preservation。
原文摘要 · Abstract (English)
Diffusion models excel at generating visually striking content from text but can inadvertently produce undesirable or harmful content when trained on unfiltered internet data. A practical solution is to selectively removing target concepts from the model, but this may impact the remaining concepts. Prior approaches have tried to balance this by introducing a loss term to preserve neutral content or a regularization term to minimize changes in the model parameters, yet resolving this trade-off remains challenging. In this work, we propose to identify and preserving concepts most affected by parameter changes, termed as \textit{adversarial concepts}. This approach ensures stable erasure with minimal impact on the other concepts. We demonstrate the effectiveness of our method using the Stable Diffusion model, showing that it outperforms state-of-the-art erasure methods in eliminating unwanted content while maintaining the integrity of other unrelated elements. Our code is available at https://github.com/tuananhbui89/Erasing-Adversarial-Preservation.
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。