Downloads · 30 days
0
FiMMIA-Image
ai-forever/FiMMIA-Image
FiMMIA-Image is a machine learning model from ai-forever. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains an implementation of FiMMIA - a modular Framework for Multimodal Membership Inference Attacks (FiMMIA)
Access
Public
Updated Nov 28, 2025
Parameters
10.1M
40.6 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors40.6 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Nov 28, 2025
- Updated
- Nov 28, 2025
- SHA
- ebd1ec09
Model card
From the Hugging Face model README
FiMMIA: scaling semantic perturbation-based membership inference across modalities
This repository contains an implementation of FiMMIA - a modular Framework for Multimodal Membership Inference Attacks (FiMMIA)
Description
The system is the first collection of models and pipelines for membership inference attacks against multimodal large language models, built initially with a priority for the Russian language, and extendable to any other language or dataset. Pipeline supports different modalities: Image, Audio and Video. In our experiments, we focus on MERA datasets, however, the model can be used to other languages.
We support models for Image (this), Audio and Video modalities.
Training and inference code can be obtained here.
- License
- mit
- Languages
- en, ru
- Created
- Nov 28, 2025
- Updated
- Nov 28, 2025