| license: mit | |
| language: | |
| - en | |
| - ru | |
| tags: | |
| - data-leakage | |
| - distribution shift | |
| - multimodal | |
| - membership inference attack | |
| # FiMMIA: scaling semantic perturbation-based membership inference across modalities | |
| This repository contains an implementation of **F**i**MMIA** - a modular **F**ramework for **M**ultimodal **M**embership **I**nference **A**ttacks (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: **Video**, Audio and Image. In our experiments, we focus on [MERA datasets](https://github.com/MERA-Evaluation/MERA), however, the model can be used to other languages. | |
| We support models for **Video** (this), [Image](https://huggingface.co/ai-forever/FiMMIA-Image) and [Audio](https://huggingface.co/ai-forever/FiMMIA-Audio) modalities. | |
| Training and inference code can be obtained [here](https://github.com/ai-forever/data_leakage_detect). | |