概念移除引导：用于安全扩散采样的证据校准负引导
Concept Removal Guidance: Evidence-Calibrated Negative Guidance for Safe Diffusion Sampling
AI总结：
提出概念移除引导（CRG），一种无需训练的方法，通过从模型噪声预测中估计不良概念存在并自适应校准负引导权重，在保持良性保真度的同时降低攻击成功率。
摘要：
文本到图像扩散模型仍然容易受到引发禁止内容的对抗性提示的影响，这促使了可靠的推理时控制。一种流行的方法是负引导，它用固定权重减去负提示方向。然而，它常常强制安全-保真度权衡，导致过度应用时产生伪影或提示漂移，而在应用不足时在攻击下失败。动态变体使用后验几率信号重新加权引导，这对于开放词汇组合提示可能很脆弱，而轻量级的基于相似性的方法忽略了沿去噪轨迹演变的图像证据。我们引入了概念移除引导（CRG），一种无需训练的方法，该方法从模型的噪声预测中估计每个扩散步骤中不需要概念的存在，并通过闭式约束更新自适应地校准负引导，该更新强制执行目标存在阈值，同时最小程度地扰动条件轨迹。在红队基准测试中，CRG在保持良性保真度的同时降低了攻击成功率，并扩展到额外的抑制目标，如艺术家风格和暴力，而无需微调或外部分类器。
英文摘要：
Text-to-image diffusion models remain vulnerable to adversarial prompts that elicit disallowed content, motivating reliable inference-time controls. A popular approach is negative guidance, which subtracts a negative prompt direction with a fixed weight. However, it often forces a safety-fidelity trade-off, causing artifacts or prompt drift when over-applied and failing under attacks when under-applied. Dynamic variants reweight guidance using posterior-odds signals, which can be brittle for open-vocabulary compositional prompts, while lightweight similarity-based methods ignore the evolving image evidence along the denoising trajectory. We introduce Concept Removal Guidance (CRG), a training-free method that estimates unwanted-concept presence at each diffusion step from the model's noise predictions, and adaptively calibrates negative guidance via a closed-form constrained update enforcing a target presence threshold while minimally perturbing the conditional trajectory. Across red-teaming benchmarks, CRG reduces attack success rates while preserving benign fidelity, and extends to additional suppression targets such as artist style and violence without fine-tuning or external classifiers.
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。
