membership-inference-attack 开源项目推荐（80 个）

privacytrustlab /ml_privacy_meter

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.

MinghuiChen43 /awesome-trustworthy-deep-learning

一份精选的可信深度学习论文列表。持续更新中……

tsinghua-fib-lab /NeurIPS2024_SPV-MIA

[NeurIPS'24] “通过自提示校准对微调大语言模型发起成员推理攻击”

OPTML-Group /Unlearn-Saliency

[ICLR24（聚焦）]《SalUn：通过基于梯度的权重显著性在图像分类与生成中赋能机器学习》，作者：Chongyu Fan*、Jiancheng Liu*、Zhang Yihua、Eric Wong、Dennis Wei、Sijia Liu

tsinghua-fib-lab /AAAI2025_MIA-Tuner

[AAAI'25 Oral] "MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector".

PrivPkt /PrivPkt

Privacy Preserving Collaborative Encrypted Network Traffic Classification (Differential Privacy, Federated Learning, Membership Inference Attack, Encrypted Traffic Classification)

jinzhuoran /RWKU

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024

liuyugeng /ML-Doctor

Code for ML Doctor

OPTML-Group /Unlearn-Sparse

[NeurIPS23（聚焦）]《模型稀疏可以简化机器学习去学习》 作者：贾景汉*、刘建成*、帕里克希特·拉姆、姚玉光、刘高文、刘杨、普拉奈·夏尔马、刘思嘉

shrebox /Privacy-Attacks-in-Machine-Learning

Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch.

zjysteven /mink-plus-plus

[ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs

MinChen00 /UnlearningLeaks

Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)

AI-SDC /SACRO-ML

Collection of tools and resources for managing the statistical disclosure control of trained machine learning models

yonsei-sslab /MIA

🔒 Implementation of Shokri et al(2016) "Membership Inference Attacks against Machine Learning Models"

Koukyosyumei /Attack_SplitNN

reveal the vulnerabilities of SplitNN

shilab /DP-MIA

Differential Privacy Protection against MembershipInference Attack on Machine Learning for Genomic Data

ganeshdg95 /Leveraging-Adversarial-Examples-to-Quantify-Membership-Information-Leakage

该项目在 GitHub 上没有填写描述

trucndt /ami

Codebase for Active Membership Inference Attack under Local Differential Privacy in Federated Learning

yyy01 /PAC

The official implementation of the paper "Data Contamination Calibration for Black-box LLMs"

Jaap-Meerhof /Federated_XGBoost_Python

FederBoost's Federated Gradient Boosting Decision Tree Algorithm, Federated enabled Membership Inference