当安全碰撞时：通过自适应安全引导解决文本到图像扩散中的多类别有害冲突
When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance
AI总结：
本文提出CASG框架，通过动态识别并应用类别对齐的安全方向，解决文本到图像扩散模型中多类别有害冲突问题，实验表明其能有效降低有害率。
摘要：
文本到图像（T2I）扩散模型在生成高质量图像方面取得了显著进展，但引发了关于有害内容生成的安全担忧。基于安全引导的方法通过将多个有害类别基于预定义关键词平均，以减轻有害输出。然而，这些方法未能捕捉不同危害类别的复杂相互作用，导致“有害冲突”，即减轻一种类型危害可能无意中加剧另一种，从而增加总体有害率。为了解决这个问题，我们提出了冲突感知自适应安全引导（CASG），一种无需训练的框架，能够在生成过程中动态识别并应用类别对齐的安全方向。CASG由两个组成部分组成：（i）冲突感知类别识别（CaCI），它识别与模型演变生成状态最一致的有害类别；（ii）冲突解决引导应用（CrGA），它仅沿着识别的类别应用安全引导以避免多类别干扰。CASG可以应用于潜在空间和文本空间的安全措施。在T2I安全基准测试中，CASG表现出最先进的性能，与现有方法相比，有害率降低了高达15.4%。
英文摘要：
Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content generation. Safety-guidance-based methods have been proposed to mitigate harmful outputs by steering generation away from harmful zones, where the zones are averaged across multiple harmful categories based on predefined keywords. However, these approaches fail to capture the complex interplay among different harm categories, leading to "harmful conflicts" where mitigating one type of harm may inadvertently amplify another, thus increasing overall harmful rate. To address this issue, we propose Conflict-aware Adaptive Safety Guidance (CASG), a training-free framework that dynamically identifies and applies the category-aligned safety direction during generation. CASG is composed of two components: (i) Conflict-aware Category Identification (CaCI), which identifies the harmful category most aligned with the model's evolving generative state, and (ii) Conflict-resolving Guidance Application (CrGA), which applies safety steering solely along the identified category to avoid multi-category interference. CASG can be applied to both latent-space and text-space safeguards. Experiments on T2I safety benchmarks demonstrate CASG's state-of-the-art performance, reducing the harmful rate by up to 15.4% compared to existing methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
