Official implementation of "Membership Inference Attacks Against Self-supervised Speech Models"

Last update: Nov 01, 2022

Related tags

Overview

Introduction

Official implementation of "Membership Inference Attacks Against Self-supervised Speech Models".

In this work, we demonstrate that existing self-supervised speech model such as HuBERT, wav2vec 2.0, CPC and TERA are vulnerable to membership inference attack (MIA) and thus could reveal sensitive informations related to the training data.

Requirements

Python >= 3.6
Install sox on your OS
Install s3prl on your OS

git clone https://github.com/s3prl/s3prl
cd s3prl
pip install -e ./

Install the specific fairseq

pip install [email protected]+https://github.com//pytorch/[email protected]#egg=fairseq

Preprocessing

First, extract the self-supervised feature of utterances in each corpus according to your needs.

Currently, only LibriSpeech is available.

BASE_PATH=/path/of/the/corpus
OUTPUT_PATH=/path/to/save/feature
MODEL=wav2vec2
SPLIT=train-clean-100 # you should extract train-clean-100, dev-clean, dev-other, test-clean, test-other

python preprocess_feature_LibriSpeech.py \
    --base_path $BATH_PATH \
    --output_path $OUTPUT_PATH \
    --model $MODEL \
    --split $SPLIT

Speaker-level MIA

After extracting the features, you can apply the attack against the models using either basic attack and improved attack.

Noted that you should run the basic attack to generate the .csv file with similarity scores before performing improved attack.

Basic Attack

SEEN_BASE_PATH=/path/you/save/feature/of/seen/corpus
UNSEEN_BASE_PATH=/path/you/save/feature/of/unseen/corpus
OUTPUT_PATH=/path/to/output/results
MODEL=wav2vec2

python predefined-speaker-level-MIA.py \
    --seen_base_path $SEEN_BATH_PATH \
    --unseen_base_path $UNSEEN_BATH_PATH \
    --output_path $OUTPUT_PATH \
    --model $MODEL \

Improved Attack

python train-speaker-level-similarity-model.py \
    --seen_base_path $UNSEEN_BATH_PATH \
    --output_path $OUTPUT_PATH \
    --model $MODEL \
    --speaker_list "${OUTPUT_PATH}/${MODEL}-customized-speaker-level-attack-similarity.csv"

python customized-speaker-level-MIA.py \
    --seen_base_path $SEEN_BATH_PATH \
    --unseen_base_path $UNSEEN_BATH_PATH \
    --output_path $OUTPUT_PATH \
    --model $MODEL \
    --similarity_model_path "${OUTPUT_PATH}/customized-speaker-similarity-model-${MODEL}.pt"

Utterance-level MIA

The process for utterance-level MIA is similar to that of speaker-level:

Basic Attack

SEEN_BASE_PATH=/path/you/save/feature/of/seen/corpus
UNSEEN_BASE_PATH=/path/you/save/feature/of/unseen/corpus
OUTPUT_PATH=/path/to/output/results
MODEL=wav2vec2

python predefined-utterance-level-MIA.py \
    --seen_base_path $SEEN_BATH_PATH \
    --unseen_base_path $UNSEEN_BATH_PATH \
    --output_path $OUTPUT_PATH \
    --model $MODEL \

Improved Attack

python train-utterance-level-similarity-model.py \
    --seen_base_path $UNSEEN_BATH_PATH \
    --output_path $OUTPUT_PATH \
    --model $MODEL \
    --speaker_list "${OUTPUT_PATH}/${MODEL}-customized-utterance-level-attack-similarity.csv"

python customized-utterance-level-MIA.py \
    --seen_base_path $SEEN_BATH_PATH \
    --unseen_base_path $UNSEEN_BATH_PATH \
    --output_path $OUTPUT_PATH \
    --model $MODEL \
    --similarity_model_path "${OUTPUT_PATH}/customized-utterance-similarity-model-${MODEL}.pt"

Citation

If you find our work useful, please cite:

Official implementation of "Membership Inference Attacks Against Self-supervised Speech Models"

Related tags

Overview

Introduction

Requirements

Preprocessing

Speaker-level MIA

Basic Attack

Improved Attack

Utterance-level MIA

Basic Attack

Improved Attack

Citation

Owner

Wei-Cheng Tseng

Repository containing the PhD Thesis "Formal Verification of Deep Reinforcement Learning Agents"

Multitask Learning Strengthens Adversarial Robustness

PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

End-to-end machine learning project for rices detection

Official Keras Implementation for UNet++ in IEEE Transactions on Medical Imaging and DLMIA 2018

A bunch of random PyTorch models using PyTorch's C++ frontend

Robot Servers and Server Manager software for robo-gym

A robust pointcloud registration pipeline based on correlation.

Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

Discover hidden deepweb pages

Transport Mode detection - can detect the mode of transport with the help of features such as acceeration,jerk etc

Causal-Adversarial-Instruments - PyTorch Implementation for Developing Library of Investigating Adversarial Examples on A Causal View by Instruments

[WWW 2022] Zero-Shot Stance Detection via Contrastive Learning

A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Deep Dual Consecutive Network for Human Pose Estimation (CVPR2021)

Learning Continuous Signed Distance Functions for Shape Representation

Solutions and questions for AoC2021. Merry christmas!

Code for the paper "Zero-shot Natural Language Video Localization" (ICCV2021, Oral).