系统评估文本生成图像模型中不适宜内容的消除效果
Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models
- 构建全流程工具包，统一评估多种概念擦除方法
- 首次系统分析不同场景下擦除效果，揭示机制与结果关联
- 为实际应用提供可操作建议，助力安全扩散模型开发
文本到图像扩散模型在多个领域广泛应用，展现出强大的创造力。然而，其强大的泛化能力可能导致生成不当内容（NSFW），对安全部署构成重大风险。尽管已有若干概念擦除方法被提出以缓解此问题，但缺乏在多种场景下对其有效性的全面评估。为此，我们引入一个完整的流程化工具包，专门用于概念擦除，并开展首个针对NSFW概念擦除方法的系统性研究。通过分析底层机制与实证观察之间的相互作用，我们提供了深入见解和实用指导，帮助在不同真实场景中有效应用概念擦除方法，旨在推进对扩散模型内容安全的理解，并为该关键领域的未来研究与发展奠定坚实基础。
原文摘要 · Abstract (English)
Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of diffusion models can inadvertently lead to the generation of not-safe-for-work (NSFW) content, posing significant risks to their safe deployment. While several concept erasure methods have been proposed to mitigate the issue associated with NSFW content, a comprehensive evaluation of their effectiveness across various scenarios remains absent. To bridge this gap, we introduce a full-pipeline toolkit specifically designed for concept erasure and conduct the first systematic study of NSFW concept erasure methods. By examining the interplay between the underlying mechanisms and empirical observations, we provide in-depth insights and practical guidance for the effective application of concept erasure methods in various real-world scenarios, with the aim of advancing the understanding of content safety in diffusion models and establishing a solid foundation for future research and development in this critical area.
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。