Privacy Inference

Privacy inference research explores how attackers can extract sensitive information from machine learning models and their outputs, undermining the privacy protections intended by federated learning and other distributed training methods. Current research focuses on developing novel attacks, such as those leveraging model gradients or generative adversarial networks, and designing defenses that balance privacy preservation with model utility, often employing techniques like differential privacy, knowledge distillation, or mixed-precision quantization. This field is crucial for ensuring responsible development and deployment of machine learning systems, particularly in sensitive domains like healthcare and finance, where data breaches can have significant consequences.

Papers

September 11, 2024

Privacy-Preserving Federated Learning with Consistency via Knowledge Distillation Using Conditional Generator
Kangyang Luo, Shuai Wang, Xiang Li, Yunshi Lan, Ming Gao, Jinlong Shu
Knowledge Distillation Strong Consistency Conditional Generation Privacy Enhancing Technology Privacy Inference

July 13, 2024

Harvesting Private Medical Images in Federated Learning Systems with Crafted Models
Shanghao Shi, Md Shahedul Haque, Abhijeet Parida, Marius George Linguraru, Y. Thomas Hou, Syed Muhammad Anwar, Wenjing Lou
Federated Learning Medical Image Secure Aggregation Privacy Inference Adversarial Model

June 4, 2024

Inference Attacks: A Taxonomy, Survey, and Promising Directions
Feng Wu, Lei Cui, Shaowen Yao, Shui Yu
Timely Survey Comprehensive Taxonomy Interpretable Direction Inference Attack Privacy Inference Privacy Breach Inference Scheme

May 24, 2024

Decaf: Data Distribution Decompose Attack against Federated Learning
Zhiyang Dai, Chunyi Zhou, Anmin Fu
Membership Inference Attack Model Inversion Attack Self Service CAFE Privacy Inference Property Inference Attack

October 11, 2023

Beyond Memorization: Violating Privacy Via Inference with Large Language Models
Robin Staab, Mark Vero, Mislav Balunović, Martin Vechev
Large Language Model LLM Inference Limited Memorization LLM Based Chatbots Text Anonymization Privacy Inference

August 25, 2023

Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs
Tianyi Zhao, Hui Hu, Lu Cheng
Graph Neural Network Integral Role Privacy Preserving Message Passing Privacy Enhancing Technology Privacy Inference

June 13, 2023

Privacy Inference-Empowered Stealthy Backdoor Attack on Federated Learning under Non-IID Scenarios
Haochen Mei, Gaolei Li, Jun Wu, Longfei Zheng
Privacy Policy Multi Scenario Backdoor Learning Stealthy Backdoor Attack Privacy Inference

January 4, 2023

Privacy and Efficiency of Communications in Federated Split Learning
Zongshun Zhang, Andrea Pinto, Valeria Turina, Flavio Esposito, Ibrahim Matta
High Efficiency Privacy Policy Timely Communication Federated Prompt Cooperation Split Learning Federated Split Learning Privacy Inference

December 21, 2022

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
Ahmed Salem, Giovanni Cherubin, David Evans, Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, Santiago Zanella-Béguelin
Machine Learning Unified Framework Membership Inference Randomized Experiment Privacy Inference Inference Privacy Game Based

November 10, 2022

Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks
Khang Tran, Phung Lai, NhatHai Phan, Issa Khalil, Yao Ma, Abdallah Khreishah, My Thai, Xintao Wu
Graph Neural Network Differential Privacy PRIvacy Leakage Privacy Protection Privacy Budget Privacy Inference

October 22, 2022

Mixed Precision Quantization to Tackle Gradient Leakage Attacks in Federated Learning
Pretom Roy Ovi, Emon Dey, Nirmalya Roy, Aryya Gangopadhyay
Differential Privacy Mixed Precision Quantization Gradient Leakage Attack Differential Privacy Noise Privacy Inference

February 10, 2022

PPA: Preference Profiling Attack Against Federated Learning
Chunyi Zhou, Yansong Gao, Anmin Fu, Kai Chen, Zhiyang Dai, Zhi Zhang, Minhui Xue, Yuqing Zhang
PRIvacy Leakage Inference Attack Privacy Inference Preference Poisoning

Privacy Inference

Papers

Privacy-Preserving Federated Learning with Consistency via Knowledge Distillation Using Conditional Generator

Harvesting Private Medical Images in Federated Learning Systems with Crafted Models

Inference Attacks: A Taxonomy, Survey, and Promising Directions

Decaf: Data Distribution Decompose Attack against Federated Learning

Beyond Memorization: Violating Privacy Via Inference with Large Language Models

Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs

Privacy Inference-Empowered Stealthy Backdoor Attack on Federated Learning under Non-IID Scenarios

Privacy and Efficiency of Communications in Federated Split Learning

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks

Mixed Precision Quantization to Tackle Gradient Leakage Attacks in Federated Learning

PPA: Preference Profiling Attack Against Federated Learning