REVIEW 2 cited by
Recovering the Pre-Fine-Tuning Weights of Generative Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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-fine-tuning 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.
Forward citations
Cited by 2 Pith papers
-
Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
Activation approximations used for faster LLM inference can dramatically increase jailbreak success rates on aligned models, and the paper's QuadA training method restores robust refusal.
-
Task-Specific Adaptation with Restricted Model Access
A new gray-box fine-tuning framework adapts frozen, hidden foundation models using only gradient access, with input/output adapters (DGA) or intermediate tokens (LGA), and matches full-access methods on several retrie...
Discussion (0). Continue with ORCID to comment.