发表机构
University of Illinois Urbana-Champaign; University of Pennsylvania; National University of Singapore（伊利诺伊大学厄巴纳-香槟分校; 宾夕法尼亚大学; 新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出CEASE方法，通过子空间约束抑制扩散模型持续概念擦除中的跨编辑干扰，实现一致的擦除-保留权衡。
AI 中文摘要
概念擦除从预训练的文本到图像扩散模型中移除受版权保护、隐私敏感或其他不受欢迎的概念，以支持内容治理和合规性。随着擦除请求随时间到来，模型必须在不撤销先前擦除的情况下移除新目标。现有方法不限制编辑之间的干扰：保留集之外的残余扰动相互作用并累积，降低无关生成的质量，有时甚至将先前擦除的目标折叠成噪声。我们提出CEASE（通过自适应子空间编辑实现持续擦除），一种无需训练的方法，在闭式求解器上施加两个子空间约束。CEASE将共享替换的令牌表示添加到求解器的不变矩阵中，并在检测到干扰时，将当前更新投影到从累积过去更新中提取的主导输出方向的正交补上。闭式分解将累积干扰归因于共享替换的重复激活和连续更新方向之间的重叠，表明这两个约束分别抑制了这些来源。在持续擦除名人、艺术风格和实例的过程中，CEASE实现了最一致的擦除-保留权衡，而现有方法要么降低通用生成质量，要么擦除目标不充分。
英文摘要
Concept erasure removes copyright-protected, privacy-sensitive, or otherwise undesirable concepts from pretrained text-to-image diffusion models to support content governance and compliance. As erasure requests arrive over time, models must remove new targets without undoing prior erasures. Existing methods do not constrain interference across edits: residual perturbations outside the retain set interact and accumulate, degrading unrelated generations and sometimes collapsing previously erased targets into noise. We propose CEASE (Continual Erasure via Adaptive Subspace Editing), a training-free method that imposes two subspace constraints on a closed-form solver. CEASE adds the token representation of the shared replacement to the solver's invariance matrix and, when interference is detected, projects the current update onto the orthogonal complement of dominant output directions extracted from cumulative past updates. A closed-form decomposition attributes the accumulated interference to repeated activation of the shared replacement and overlap between successive update directions, showing that the two constraints suppress these respective sources. Across continual erasure of celebrities, artistic styles, and instances, CEASE achieves the most consistent erase-preserve trade-off, while existing methods either degrade general generation or insufficiently erase targets.
Comments24 pages. Project page: https://continual-erasure.cvmlgroup.web.illinois.edu/
