Metraipolis › archive › dc_cd5de9956c5f
On-the-go Forgetting without Explicit Unlearning via ERASE — arXiv:2609.05966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05966
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:56:28.483Z
- SHA-256 of the archived text
4fbf9778a876cd22f6e65f6a7ba67304a5bd69aec0a057f7b601b30205a5da82- Stable URL of this page
https://metraipolis.com/documento/dc_cd5de9956c5f
How to cite
On-the-go Forgetting without Explicit Unlearning via ERASE — arXiv:2609.05966 — arXiv (en), https://arxiv.org/abs/2609.05966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd5de9956c5f (Metraipolis archive dc_cd5de9956c5f, sha256 4fbf9778a876cd22f6e65f6a7ba67304a5bd69aec0a057f7b601b30205a5da82)
BibTeX
@misc{dccd5de9956c5f,
title = {On-the-go Forgetting without Explicit Unlearning via ERASE — arXiv:2609.05966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd5de9956c5f; sha256 4fbf9778a876cd22f6e65f6a7ba67304a5bd69aec0a057f7b601b30205a5da82},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing unlearning approaches typically rely on post hoc weight adaptation or distillation, leading to duplicated memory costs, degraded generalization, and limited scalability. In this work, we introduce ERASE, Erasure via Reconstructive Adversarial Signal Editing, a framework for on-the-go forgetting that suppresses the observable influence of private data without modifying model weights. ERASE leverages structured, class-conditioned input perturbations to induce selective forgetting during inference, eliminating the need for retraining, fine-tuning, or model copies. We rigorously characterize sufficient conditions when ERASE provably achieves functional forgetting of designated subclasses while preserving predictions across other subclasses within the same superclass. This analysis offers a principled foundation for inference-time forgetting under mild regularity assumptions. Across diverse architectures and benchmark datasets, ERASE maintains the best observed balance between forgetting efficacy, computational efficiency, and retention fidelity over recent unlearning-based methods. By reimagining data removal as forgetting without unlearning, our work establishes a scalable, regulation-aligned pathway for continual, privacy-conscious learning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.05966 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T13:39:42.828Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).