Skip to content
AI News HubLIVE
Original source2 min read

Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning

Summary

This arXiv paper argues that diffusion data-point unlearning is usually evaluated right after each deletion, ignoring what happens when many deletion requests repeatedly update the same model. The authors identify “sequential reappearance,” a failure mode in which an instance judged forgotten later returns to the memorized regime without reuse of the deleted data or adversarial fine-tuning. They introduce a target-level evaluation protocol and find that reappearing targets show sharper local denoising-loss geometry after deletion.

SourcearXiv Machine LearningAuthor: Donghyun Kim, Taehyuk Lee, Jinyeong Kim, Youngmin Oh, Dohyeong Kim, Jaehyuk Ryu, Sangwoo Hong
Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 21 Sep 2026]

Title:Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning

View a PDF of the paper titled Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning, by Donghyun Kim and 6 other authors

View PDF HTML (experimental)

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.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.25166 [cs.LG]

(or arXiv:2609.25166v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.25166

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Sangwoo Hong [view email] [v1] Mon, 21 Sep 2026 12:52:22 UTC (43,603 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning, by Donghyun Kim and 6 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

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.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Introduces “sequential reappearance”: a deleted instance judged forgotten later returns to the memorized regime, with no data reuse or adversarial fine-tuning required
  • Proposes a target-level protocol tracking whether each target is forgotten immediately, stays forgotten at sequence end, or reappears during later deletions
  • Finds reappearing targets exhibit sharper local denoising-loss geometry after deletion, offering a diagnostic signal
  • arXiv:2609.25166, by Donghyun Kim and six co-authors, listed under cs.LG and cs.AI

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models