Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.25166v1 Announce Type: cross Abstract: 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…

science

Sources

• T1Mitigating Sequential Reappearance in Diffusion Data-Point UnlearningarXiv24 Sept, 04:00