Duplicate from ai-forever/FiMMIA-Video

Co-authored-by: ai-forever <ai-forever@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,22 @@
+---
+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).
+

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4a430fd4ab0c004b3031c3816b85c90808fe02b646f6c19214fa358daacb32
+size 40562464

sigmas.json

@@ -0,0 +1 @@
+{"ruHHH-Video_Qwen2.5-VL-3B-Instruct": {"mean": -0.09843602534990105, "std": 0.2069565781774879}, "CommonVideoQA_Qwen2.5-VL-3B-Instruct": {"mean": 0.009537732455924316, "std": 0.15681258803478634}, "RealVideoQA_Qwen2.5-VL-3B-Instruct": {"mean": -0.05630002666418224, "std": 0.20136335094656027}, "ruHHH-Video_Qwen2.5-VL-7B-Instruct": {"mean": -0.13990224538014884, "std": 0.21727828640735594}, "CommonVideoQA_Qwen2.5-VL-7B-Instruct": {"mean": -0.1832180926517355, "std": 0.265920142721381}, "RealVideoQA_Qwen2.5-VL-7B-Instruct": {"mean": -0.17230708691985333, "std": 0.2674634915101069}, "ruHHH-Video_LLaVA-NeXT-Video-7B-hf": {"mean": 1.1392326339277818, "std": 0.6870219735441873}, "CommonVideoQA_LLaVA-NeXT-Video-7B-hf": {"mean": 1.1727398112089336, "std": 0.6357065728666026}, "RealVideoQA_LLaVA-NeXT-Video-7B-hf": {"mean": 1.1784212428367942, "std": 0.6513109389077784}, "ruHHH-Video_LLaVA-NeXT-Video-7B-DPO-hf": {"mean": 1.1368909902922453, "std": 0.6780120522105653}, "CommonVideoQA_LLaVA-NeXT-Video-7B-DPO-hf": {"mean": 1.1527764159483844, "std": 0.5991938726807061}, "RealVideoQA_LLaVA-NeXT-Video-7B-DPO-hf": {"mean": 1.1699209121316279, "std": 0.635722887739348}}