FiMMIA
Collection
FiMMIA: scaling semantic perturbation-based membership inference across modalities.
•
3 items
•
Updated
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.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support