正本清源：自動導航去噪軌跡以規避不良概念

Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts

April 17, 2025

作者: Leyang Li, Shilin Lu, Yan Ren, Adams Wai-Kin Kong

cs.AI

摘要

確保文本到圖像模型的倫理部署，需要有效技術來防止生成有害或不當內容。雖然概念擦除方法提供了一個有前景的解決方案，但現有的基於微調的方法存在顯著限制。無錨方法可能破壞採樣軌跡，導致視覺偽影，而有錨方法則依賴於啟發式選擇的錨概念。為克服這些不足，我們引入了一個名為ANT的微調框架，它能自動引導去噪軌跡以避免不需要的概念。ANT基於一個關鍵洞察：在去噪的中後期階段反轉無分類器引導的條件方向，可以在不犧牲早期結構完整性的前提下實現精確的內容修改。這啟發了一種軌跡感知的目標函數，它保持了早期階段分數函數場的完整性，引導樣本向自然圖像流形靠近，而無需依賴啟發式的錨概念選擇。對於單一概念擦除，我們提出了一種增強型權重顯著性圖，以精確識別對不需要概念貢獻最大的關鍵參數，從而實現更徹底和高效的擦除。對於多概念擦除，我們的目標函數提供了一個靈活的即插即用解決方案，顯著提升了性能。大量實驗表明，ANT在單一和多概念擦除方面均達到了最先進的成果，在不損害生成保真度的前提下，輸出了高質量且安全的結果。代碼可在https://github.com/lileyang1210/ANT 獲取。

English

Ensuring the ethical deployment of text-to-image models requires effective techniques to prevent the generation of harmful or inappropriate content. While concept erasure methods offer a promising solution, existing finetuning-based approaches suffer from notable limitations. Anchor-free methods risk disrupting sampling trajectories, leading to visual artifacts, while anchor-based methods rely on the heuristic selection of anchor concepts. To overcome these shortcomings, we introduce a finetuning framework, dubbed ANT, which Automatically guides deNoising Trajectories to avoid unwanted concepts. ANT is built on a key insight: reversing the condition direction of classifier-free guidance during mid-to-late denoising stages enables precise content modification without sacrificing early-stage structural integrity. This inspires a trajectory-aware objective that preserves the integrity of the early-stage score function field, which steers samples toward the natural image manifold, without relying on heuristic anchor concept selection. For single-concept erasure, we propose an augmentation-enhanced weight saliency map to precisely identify the critical parameters that most significantly contribute to the unwanted concept, enabling more thorough and efficient erasure. For multi-concept erasure, our objective function offers a versatile plug-and-play solution that significantly boosts performance. Extensive experiments demonstrate that ANT achieves state-of-the-art results in both single and multi-concept erasure, delivering high-quality, safe outputs without compromising the generative fidelity. Code is available at https://github.com/lileyang1210/ANT