{"slug": "mitigating-sequential-reappearance-in-diffusion-data-point-unlearning", "title": "Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning", "summary": "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.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 21 Sep 2026]\n\n# Title:Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning\n\n[View PDF](https://arxiv.org/pdf/2609.25166)\n\n[HTML (experimental)](https://arxiv.org/html/2609.25166v1)\n\nAbstract: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.\n    \n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/mitigating-sequential-reappearance-in-diffusion-data-point-unlearning", "canonical_source": "https://arxiv.org/abs/2609.25166", "published_at": "2026-09-23 04:00:00+00:00", "updated_at": "2026-09-23 04:24:56.582329+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "ai-safety", "generative-ai"], "entities": ["arXiv", "diffusion data-point unlearning", "sequential reappearance"], "alternates": {"html": "https://wpnews.pro/news/mitigating-sequential-reappearance-in-diffusion-data-point-unlearning", "markdown": "https://wpnews.pro/news/mitigating-sequential-reappearance-in-diffusion-data-point-unlearning.md", "text": "https://wpnews.pro/news/mitigating-sequential-reappearance-in-diffusion-data-point-unlearning.txt", "jsonld": "https://wpnews.pro/news/mitigating-sequential-reappearance-in-diffusion-data-point-unlearning.jsonld"}}