Methods › General › Fine-Tuning › Spectral DeTuning
Spectral DeTuning
Introduced by Eliahu Horwitz et al. in Recovering the Pre-Fine-Tuning Weights of Generative Models
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A method that can recover the weights of the pre-fine-tuning model using a few low-rank (LoRA) fine-tuned models. In contrast to previous attacks that attempt to recover pre-fine-tuning capabilities, Spectral DeTuning aims to recover the exact pre-fine-tuning weights. Spectral DeTuning can exploit this vulnerability against large-scale models such as a personalized Stable Diffusion and an aligned Mistral.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Recovering the Pre-Fine-Tuning Weights of Generative Models 15 Feb 2024 · 1 repository · arXiv:2402.10208Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
Tasks archive 2025-07-28
1 task the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Pre-Fine-Tuning Weight Recovery | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections