cd /news/machine-learning/mitigating-sequential-reappearance-i… · home topics machine-learning article
[ARTICLE · art-137787] src=arxiv.org ↗ pub= topic=machine-learning verified=true sentiment=· neutral

Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning

A September 21, 2026 arXiv paper submitted to the Computer Science > Machine Learning category identifies "sequential reappearance," a failure mode in diffusion data-point unlearning where an instance initially judged forgotten returns to the memorized regime without reuse of the deleted data or adversarial fine-tuning. The authors 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, and report that targets which later reappear exhibit sharper local denoising-loss geometry after deletion than targets that remain forgotten.

by read2 min views1 publishedSep 23, 2026
Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning
Image: source
  [Submitted on 21 Sep 2026]


[View PDF](https://arxiv.org/pdf/2609.25166)

[HTML (experimental)](https://arxiv.org/html/2609.25166v1)

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 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.

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?) alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?) Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?) IArxiv Recommender

(What is IArxiv?) arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

── more in #machine-learning 4 stories · sorted by recency
── more on @arxiv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/mitigating-sequentia…] indexed:0 read:2min 2026-09-23 ·