MANCE：流形感知的概念擦除

摘要

概念擦除旨在从表征中移除目标概念，同时保留其中编码的其他信息。这一任务颇具挑战，因为表征编码了许多概念，而这些概念往往与擦除目标存在关联，因此移除目标可能会损害其他概念。我们提出流形约束假说（MCH）：如果自然表征集中于结构化的低维流形，则在干预过程中，应将干预约束在该流形内，从而更好地保留表征中编码的其他信息。我们将MCH实现为一种新的概念擦除方法：流形感知概念擦除（MANCE）。MANCE利用预测目标概念的分类器信号，对表征进行迭代更新。我们通过自然输入获得的表征来估计流形，然后将概念移除更新投影到估计的流形上。我们在涵盖文本和视觉的119种设置上进行了广泛评估，包括13个语言模型、三个NLP概念以及40个CelebA-CLIP属性。在先前方法基础上应用MANCE，一致地改善了泄露结果。我们还引入了MANCE+和MANCE++，它们在采用MANCE之前先进行闭式擦除算法，与匹配的全空间更新相比，实现了更好的泄露与精确性权衡。我们的最佳方法MANCE++在非线性概念擦除上取得了最先进的结果。这些结果在擦除场景下支持了MCH：应当将干预约束在自然表征流形内。

English

Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many concepts that are often correlated with the erasure target, so removing the target risks damaging them. We propose the Manifold Constraint Hypothesis (MCH): if natural representations concentrate on a structured, lower-dimensional manifold, then interventions should be constrained to that manifold and better preserve other information encoded in the representation during interventions. We instantiate MCH in a new concept erasure method: MANifold aware Concept Erasure (MANCE). MANCE performs iterative updates to the representations using signals from a classifier that predicts a target concept. We estimate the manifold using representations obtained from natural inputs, and then we project the concept removal update to the estimated manifold. We perform extensive evaluation on 119 settings spanning text and vision, including 13 language models, three NLP concepts, and 40 CelebA-CLIP attributes. Employing MANCE on top of previous methods shows consistent improved leakage results. We also introduce MANCE+ and MANCE++, which prepend a closed-form erasure algorithm before employing MANCE, achieving better leakage--surgicality tradeoffs relative to matched full-space updates. MANCE++, our best method, achieves state-of-the-art results on nonlinear concept erasure. These results support MCH in the erasure setting: interventions should be constrained to the natural representation manifold.