REVIEW 6 cited by
Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing
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
Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing
read the original abstract
Model merging leverages multiple finetuned expert models to construct a multi-task model with low cost, and is gaining increasing attention. However, as a growing number of finetuned models become publicly available, concerns about the safety of model merging have emerged. Unauthorized merging may infringe on developers' rights and risk leaking sensitive personal information. Most existing methods focus on detecting whether a merged model originates from a specific source model, but fail to effectively prevent illegal merging. In this paper, we propose MergeLock, an active protection mechanism that disrupts model parameters to render them unmergeable, thereby directly preventing unauthorized model merging. Specifically, leveraging the inherent symmetry of the attention mechanism in Transformer-based models, we randomly sample two pairs of invertible matrices and apply them to the Query-Key (QK) and Value-Output (VO) branches. This transformation keeps the model's output unchanged while pushing it away from the shared parameter space of other finetuned models. Extensive experiments across both vision and language tasks demonstrate that MergeLock can degrade the performance of merged models by over 95% when a protected model is involved in most cases, demonstrating its effectiveness. Moreover, we further demonstrate that merged models protected by MergeLock cannot be effectively recovered using low-cost restoration methods, further enhancing robustness against unauthorized merging. The code is available at https://github.com/hetailang/Merge-Lock.
Forward citations
Cited by 6 Pith papers
-
Efficient Decentralized Multi-task Dataset Valuation via Model Merging
Task-arithmetic model merging approximates multi-task coalition utilities well enough to recover Dataset Shapley rankings privately and without retraining.
-
Locking Pretrained Weights via Deep Low-Rank Residual Distillation
DLR-Lock locks open-weight LLMs against unauthorized fine-tuning by swapping MLPs for deep low-rank residual networks that inflate backprop memory and complicate optimization, yet preserve original capabilities via mo...
-
Generalizing the Geometry of Model Merging Through Frechet Averages
Model merging is reframed as Fréchet averaging on manifolds whose geometry respects architectural symmetries, generalizing Fisher merging and enabling better LoRA merges.
-
Generalizing the Geometry of Model Merging Through Frechet Averages
Model merging is generalized as Fréchet averaging on symmetry-invariant manifolds, containing Fisher merging as a special case and offering a new approach for LoRA adapters.
-
Making Models Unmergeable via Scaling-Sensitive Loss Landscape
TRAP² fine-tunes model updates so that standalone accuracy stays high while any re-scaling during merging reliably collapses task accuracy, across transformer and ConvNeXt backbones.
-
On the Vulnerability of Parameter-Level Defenses to Model Merging
Parameter-level defenses for model merging are vulnerable to Anchor-Guided Attack because protected weights are dominated by the pretrained model, and a new defense ARF is introduced to counter it.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.