Membership Inference Attack

Membership inference attacks (MIAs) aim to determine if a specific data point was used to train a machine learning model, posing a significant privacy risk. Current research focuses on evaluating MIA effectiveness across various model architectures, including large language models (LLMs), diffusion models, and vision transformers, and exploring the impact of different training methods and data characteristics on attack success. The reliability and accuracy of MIAs themselves are under scrutiny, with some studies highlighting limitations and overestimation of their capabilities, particularly in realistic settings. Understanding the vulnerabilities and limitations of MIAs is crucial for developing effective privacy-preserving techniques and for responsibly deploying machine learning models.

Papers

February 2, 2024

Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization
Arezoo Rajabi, Reeya Pimple, Aiswarya Janardhanan, Surudhi Asokraj, Bhaskar Ramasubramanian, Radha Poovendran
Transfer Learning Supervised ImageNet Black Box Membership Inference Attack Randomization Program Deep Neural Network Performance Label Only Membership Inference Attack

January 29, 2024

Scalable Federated Unlearning via Isolated and Coded Sharding
Yijing Lin, Zhipeng Gao, Hongyang Du, Dusit Niyato, Gui Gui, Shuguang Cui, Jinke Ren
Membership Inference Attack Unlearning Framework Federated Unlearning Table Sharding

January 24, 2024

January 18, 2024

Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
Janvi Thakkar, Giulio Zizzo, Sergio Maffeis
Adversarial Training Membership Inference Attack Empirical Evaluation Differentially Private Robust Adversarial Learning Simultaneous Attack Private Probabilistic

January 10, 2024

Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks
Haonan Shi, Tu Ouyang, An Wang
Machine Learning Model Membership Inference Attack Sensitive Data

December 8, 2023

Membership Inference Attacks on Diffusion Models via Quantile Regression
Shuai Tang, Zhiwei Steven Wu, Sergul Aydore, Michael Kearns, Aaron Roth
Diffusion Model Membership Inference Attack Privacy Risk Shadow Model

December 7, 2023

Diffence: Fencing Membership Privacy With Diffusion Models
Yuefeng Peng, Ali Naseh, Amir Houmansadr
Diffusion Model Membership Inference Attack State of the Art Defense Membership Privacy Prior Defense

December 6, 2023

Low-Cost High-Power Membership Inference Attacks
Sajjad Zarifzadeh, Philippe Liu, Reza Shokri
Membership Inference Attack Privacy Risk Likelihood Ratio Test

November 29, 2023

Addressing Membership Inference Attack in Federated Learning with Model Compression
Gergely Dániel Németh, Miguel Ángel Lozano, Novi Quadrianto, Nuria Oliver
Federated Learning Membership Inference Attack Privacy Preserving Model Compression Privacy Enhancing Technology Agnostic Federated Learning

November 28, 2023

MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning
Soumya Banerjee, Sandip Roy, Sayyed Farid Ahamed, Devin Quinn, Marc Vucovich, Dhruv Nandakumar, Kevin Choi, Abdul Rahman, Edward Bowen, Sachin Shetty
Constructive Approach Membership Inference Attack Faulty Negative Mitigation Privacy Preserving Machine Learning Attack Dataset

November 27, 2023

Using Decentralized Aggregation for Federated Learning with Differential Privacy
Hadeel Abd El-Kareem, Abd El-Moaty Saleh, Ana Fernández-Vilas, Manuel Fernández-Veiga, asser El-Sonbaty
Differential Privacy Membership Inference Attack Personal Information Privacy Breach Decentralized Aggregation

November 26, 2023

Confidence Is All You Need for MI Attacks
Abhishek Sinha, Himanshi Tibrewal, Mansi Gupta, Nikhar Waghela, Shivank Garg
Training Data Machine Learning Model Membership Inference Attack Sensitive Data High Confidence Label Attack MI Attack

November 15, 2023

Privacy Threats in Stable Diffusion Models
Thomas Cilloni, Charles Fleming, Charles Walter
Diffusion Model Membership Inference Attack Stable Diffusion Stable Diffusion Model Robust Defense Privacy Threat

November 12, 2023

Preserving Node-level Privacy in Graph Neural Networks
Zihang Xiang, Tianhao Wang, Di Wang
Graph Neural Network Differential Privacy Membership Inference Attack Node Level Privacy

November 10, 2023

Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
Wenjie Fu, Huandong Wang, Chen Gao, Guanghua Liu, Yong Li, Tao Jiang
Language Model Membership Inference Attack Prompt Tuning Fine Tuned Large Language Model Based Attack

November 7, 2023

When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
Huan Tian, Guangsheng Zhang, Bo Liu, Tianqing Zhu, Ming Ding, Wanlei Zhou
Procedural Fairness Membership Inference Attack Privacy Policy Model Fairness Fairness Method Privacy Threat

November 6, 2023

Preserving Privacy in GANs Against Membership Inference Attack
Mohammadhadi Shateri, Francisco Messina, Fabrice Labeau, Pablo Piantanida
Generative Adversarial Network Membership Inference Attack Privacy Enhancing Technology

November 2, 2023

MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training
Jiacheng Li, Ninghui Li, Bruno Ribeiro
Membership Inference Attack Membership Inference Counterfactual Representation

October 30, 2023

Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
Minxing Zhang, Ning Yu, Rui Wen, Michael Backes, Yang Zhang
Generative Model Generative Adversarial Network Membership Inference Attack