通过交叉注意力激活投影实现扩散模型的概念遗忘
Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
AI总结：
提出PURE方法，利用交叉注意力激活空间构建遗忘和保留基，通过线性投影编辑权重，在保持保留概念的同时有效消除目标概念。
摘要：
概念遗忘旨在从预训练的文本到图像扩散模型中擦除目标概念，而无需重新训练。闭式方法在此设置中具有吸引力，因为它们对交叉注意力权重应用单一确定性编辑，并且不增加推理时间成本。然而，现有的闭式方法通过文本编码器对少数命名目标概念的简短锚定提示的响应来表示目标概念，而唤起该概念但不一致命名的释义提示可以绕过编辑。我们认为，目标应该改为在交叉注意力激活空间中表示。文本嵌入描述用户的提示，而交叉注意力激活描述模型即将渲染的内容，后者泛化到锚定模板未覆盖的释义。基于这一观察，我们提出了PURE（U-Net渲染中的投影用于擦除），这是一种闭式方法，从沿短去噪轨迹捕获的逐层交叉注意力激活构建遗忘和保留基，并将单个线性投影器应用于交叉注意力键和值权重。在最近涵盖艺术风格、知识产权、名人和NSFW类别中十个概念的整体概念遗忘基准上，PURE显著减少了在释义和对抗性提示下的目标泄露，同时将保留概念保持接近未编辑模型，在评估方法中实现了最佳的总体遗忘-保留权衡。
英文摘要：
Existing closed-form methods for concept unlearning in text-to-image diffusion models typically derive editing directions from fixed text embeddings, which may not fully capture how concepts are expressed across latent states, timesteps, and layers. To capture this variation, we investigate cross-attention activations collected during denoising. In controlled probing experiments using the same anchor prompts, activation-derived bases achieve approximately five times the recall of text-derived bases on held-out prompts expressing the target concepts. Based on this finding, we propose Cross-Attention Subspace Erasure (CASE), a closed-form method that constructs layer-specific forget and retain subspaces from cross-attention activations. These subspaces define a retain-constrained linear operator incorporated directly into cross-attention weights, requiring no gradient-based fine-tuning or additional inference-time computation. Across ten concepts spanning four categories, CASE achieves the highest harmonic-mean score among evaluated baselines in all four categories, balancing suppression, retention, adversarial robustness, and generation quality. Further experiments demonstrate robustness to recovery attacks and a favorable suppression-retention trade-off when jointly unlearning up to 100 artistic styles. The benefits of activation-derived editing also extend to larger diffusion models, including SDXL and FLUX.
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。
