Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning

The paper introduces a new evaluation protocol for diffusion data‑point unlearning that tracks whether each target is forgotten, remains forgotten, or reappears during subsequent deletions. It identifies a failure mode called sequential reappearance, where an instance that was initially forgotten later returns to the memorized regime without re‑use of the deleted data or adversarial fine‑tuning. The study also finds that reappearing targets exhibit a sharper local denoising‑loss geometry after deletion than those that remain forgotten.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• diffusion
• fine-tuning
• safety