A curated list of trustworthy deep learning papers. Daily updating...
-
Updated
May 24, 2024
A curated list of trustworthy deep learning papers. Daily updating...
The official implementation of the paper "Data Contamination Calibration for Black-box LLMs" (ACL 2024)
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu
The source code of the paper "Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks"(EuroS&P 2024)
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
Collection of tools and resources for managing the statistical disclosure control of trained machine learning models
This repository accompanies the paper "SynthShield: Leveraging Synthetic Distributions to Enhance Privacy Against Membership Inference" currently under review at the International Conference on Pattern Recognition (ICPR). It contains the main code used in applying and analysing the SynthShield technique analysed in the paper.
Min-K%++: Improved baseline for detecting pre-training data of LLMs https://arxiv.org/abs/2404.02936
[NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
Performing membership inference attack (MIA) against Korean language models (LMs).
Privacy in Practice: Private COVID-19 Detection in X-Ray Images
Codebase for Active Membership Inference Attack under Local Differential Privacy in Federated Learning
FederBoost's Federated Gradient Boosting Decision Tree Algorithm, Federated enabled Membership Inference
Code for ML Doctor
DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch.
Privacy Preserving Collaborative Encrypted Network Traffic Classification (Differential Privacy, Federated Learning, Membership Inference Attack, Encrypted Traffic Classification)
Microsoft's Membership Inference Competition (MICO) for CIFAR10 using shadow models.
A mitigation method against privacy violation attacks on face recognition systems
Add a description, image, and links to the membership-inference-attack topic page so that developers can more easily learn about it.
To associate your repository with the membership-inference-attack topic, visit your repo's landing page and select "manage topics."