发表机构
Konkuk University（建国大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对扩散模型数据点遗忘中反复删除导致的顺序重现问题，提出目标级评估协议，并发现重现目标具有更尖锐的局部去噪损失几何结构。
AI 中文摘要
扩散数据点遗忘通常在每次删除后立即进行评估，尽管后续请求可能会反复更新同一模型。我们发现了顺序重现这一失效模式，即一个最初被判定为已遗忘的实例，在未使用被删除数据或进行对抗性微调的情况下，后来重新回到记忆状态。为捕捉这一行为，我们引入了一种目标级评估协议，该协议跟踪每个目标是否在删除后立即被遗忘、在序列结束时仍保持遗忘状态，或在后续删除过程中重新出现。我们进一步发现，后来重新出现的目标在删除后比保持遗忘的目标表现出更尖锐的局部去噪损失几何结构。
英文摘要
Diffusion data-point unlearning is typically evaluated immediately after each deletion, even though subsequent requests may repeatedly update the same model. We identify sequential reappearance, a failure mode in which an instance that is initially judged to be forgotten later returns to the memorized regime without reuse of the deleted data or adversarial fine-tuning. To capture this behavior, we introduce a target-level evaluation protocol that tracks whether each target is forgotten immediately, remains forgotten at the end of the sequence, or reappears during subsequent deletions. We further find that targets that later reappear exhibit sharper local denoising-loss geometry after deletion than targets that remain forgotten.
