arxiv
PublishedSeptember 4, 2026 at 4:00 AM
—neutral
Extracting Forgotten Prompts from Targeted Unlearned Models
Publisher summary· verbatim
arXiv:2609.03662v1 Announce Type: new Abstract: Recent unlearning methods (e.g. NPO, DPO, LUNAR) make use of refusal alignment to suppress forgotten data. However, it has been shown that refusal responses might leave traces of unlearning, and recent attacks have been able to successfully recover som
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
The Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗