Do Influence-Derived Data Perturbations Enable Machine Unlearning? A Controlled Study of Three Plausible Roles
This story is from 2026-09-14. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.12313v1 Announce Type: new Abstract: We evaluate Deep Perturbation Learning (DPL), which perturbs training images and labels along influence-derived directions, in three roles in which prior work has positioned it for machine unlearning: a direct deletion signal (the strongest claim), a…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-09-14 04:00 · arXiv cs.AI
Do Influence-Derived Data Perturbations Enable Machine Unlearning? A Controlled Study of Three Plausible Roles