Privacy Preserving

Privacy-preserving techniques aim to enable data analysis and machine learning while safeguarding sensitive information. Current research focuses on developing and improving methods like differential privacy, federated learning, homomorphic encryption, and data obfuscation, often applied to specific model architectures such as transformers and neural radiance fields. These advancements are crucial for addressing privacy concerns in various applications, including healthcare, finance, and AI-powered services, allowing for collaborative data analysis and model training without compromising individual privacy. The field is actively exploring the trade-offs between privacy guarantees, model accuracy, and computational efficiency.

Papers

December 7, 2023

Making Translators Privacy-aware on the User's Side
Ryoma Sato
Machine Translation Privacy Preserving Machine Translation System USER Provided Name

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 24, 2023

DP-NMT: Scalable Differentially-Private Machine Translation
Timour Igamberdiev, Doan Nam Long Vu, Felix Künnecke, Zhuo Yu, Jannik Holmer, Ivan Habernal
Machine Translation Neural Machine Translation Privacy Preserving Private Stochastic

November 19, 2023

Large-scale Mixed Traffic Control Using Dynamic Vehicle Routing and Privacy-Preserving Crowdsourcing
Dawei Wang, Weizi Li, Jia Pan
Privacy Preserving Crowdsourcing Context Mixed Traffic Mobile Crowdsensing Mixed Traffic Control

November 12, 2023

November 6, 2023

Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems
Derek Lilienthal, Paul Mello, Magdalini Eirinaki, Stas Tiomkin
Generative Adversarial Network Generative AI Recommender System Privacy Preserving Resolution Diffusion

October 30, 2023

PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learning
Tianyue Chu, Mengwei Yang, Nikolaos Laoutaris, Athina Markopoulou
Federated Learning Privacy Preserving Model Pruning Privacy Enhancing Technology Privacy Accuracy

October 29, 2023

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Active Data Manipulation
Dzung Pham, Shreyas Kulkarni, Amir Houmansadr
Federated Learning Privacy Preserving Secure Aggregation Empirical Privacy Reconstruction Attack

October 28, 2023

Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation
Kunlin Cai, Jinghuai Zhang, Will Shand, Zhiqing Hong, Guang Wang, Desheng Zhang, Jianfeng Chi, Yuan Tian
Study Feature Privacy Preserving Privacy Risk Privacy Attack Mobility Data

October 24, 2023

On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
Rongzhe Wei, Eleonora Kreačić, Haoyu Wang, Haoteng Yin, Eli Chien, Vamsi K. Potluru, Pan Li
Differential Privacy Privacy Preserving PRIvacy Leakage Privacy Preservation Discrete Diffusion Model Inherent Privacy Discrete Denoising Diffusion

October 5, 2023

PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction
Saifullah Saifullah, Stefan Agne, Andreas Dengel, Sheraz Ahmed
Differential Privacy Privacy Preserving Private Federated Learning Key Information Extraction

October 4, 2023

Shielding the Unseen: Privacy Protection through Poisoning NeRF with Spatial Deformation
Yihan Wu, Brandon Y. Feng, Heng Huang
Neural Radiance Field Privacy Preserving 3D Scene Reconstruction Deformation Field Unseen Video Projected Gradient Descent

September 28, 2023

Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning
Wenke Huang, Mang Ye, Zekun Shi, Bo Du
Privacy Preserving Federated Setting Federated Distillation

September 27, 2023

A Unified View of Differentially Private Deep Generative Modeling
Dingfan Chen, Raouf Kerkouche, Mario Fritz
Privacy Preserving Unified View Private Generative Model Privacy Preserving Learning Private Data Generation

September 19, 2023

September 15, 2023

hear-your-action: human action recognition by ultrasound active sensing
Risako Tanigawa, Yasunori Ishii
Action Recognition Privacy Preserving Support Vector Machine Human Action Recognition Non Invasive Active Sensing

September 7, 2023

FisheyePP4AV: A privacy-preserving method for autonomous vehicles on fisheye camera images
Linh Trinh, Bach Ha, Tu Tran
Autonomous Driving Autonomous Vehicle Privacy Preserving Fisheye Camera Fisheye Image Fisheye Video VidSGG Datasets

September 2, 2023

PFL-LSTR: A privacy-preserving framework for driver intention inference based on in-vehicle and out-vehicle information
Runjia Du, Pei Li, Sikai Chen, Samuel Labi
Privacy Preserving Vehicle Interaction Intelligent Vehicle Vehicle Image Intention Prediction

Privacy Preserving

Papers

Making Translators Privacy-aware on the User's Side

Addressing Membership Inference Attack in Federated Learning with Model Compression

DP-NMT: Scalable Differentially-Private Machine Translation

Large-scale Mixed Traffic Control Using Dynamic Vehicle Routing and Privacy-Preserving Crowdsourcing

pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharing

Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark

Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems

PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learning

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Active Data Manipulation

Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation

On the Inherent Privacy Properties of Discrete Denoising Diffusion Models

PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction

Shielding the Unseen: Privacy Protection through Poisoning NeRF with Spatial Deformation

Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning

A Unified View of Differentially Private Deep Generative Modeling

DPpack: An R Package for Differentially Private Statistical Analysis and Machine Learning

Crypto'Graph: Leveraging Privacy-Preserving Distributed Link Prediction for Robust Graph Learning

hear-your-action: human action recognition by ultrasound active sensing

FisheyePP4AV: A privacy-preserving method for autonomous vehicles on fisheye camera images

PFL-LSTR: A privacy-preserving framework for driver intention inference based on in-vehicle and out-vehicle information