SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.10208 · ICML · 2024

Recovering the Pre-Fine-Tuning Weights of Generative Models

Yedid Hoshen, Eliahu Horwitz, Jonathan Kahana

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
eliahuhorwitz/Spectral-DeTuning canonical 2 of 4
FunctionStatusWhere it lives
IncreaseRankOnPlateau Ran eliahuhorwitz/Spectral-DeTuning/spectral_detuning.py
pointer only (licence: NOASSERTION) · get_code("bfdada99eaa9611a")
calc_loss Ran eliahuhorwitz/Spectral-DeTuning/spectral_detuning.py
pointer only (licence: NOASSERTION) · get_code("69b972e54e2a148f")
merge_lora_weights Not yet run eliahuhorwitz/Spectral-DeTuning/spectral_detuning.py
pointer only (licence: NOASSERTION) · get_code("110c9bdd42e071fb")
recover_layer Not yet run eliahuhorwitz/Spectral-DeTuning/spectral_detuning.py
pointer only (licence: NOASSERTION) · get_code("56be80e64031c8cf")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The dominant paradigm in generative modeling consists of two steps: i) pre-training on a large-scale but unsafe dataset, ii) aligning the pre-trained model with human values via fine-tuning. This practice is considered safe, as no current method can recover the unsafe, pre-fine-tuning model weights. In this paper, we demonstrate that this assumption is often false. Concretely, we present Spectral DeTuning, 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-finetuning capabilities, our method aims to recover the exact pre-fine-tuning weights. Our approach exploits this new vulnerability against large-scale models such as a personalized Stable Diffusion and an aligned Mistral.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.10208")
get_code_for_paper("2402.10208")
have("2402.10208")

Connect an agent — have() is free.