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

March 24, 2022

SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning
Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Songze Li, Giuseppe Caire
Federated Learning Privacy Preserving Secure Aggregation SWIFT DynGFN Optimal Communication

March 22, 2022

SPRITE: A Scalable Privacy-Preserving and Verifiable Collaborative Learning for Industrial IoT
Jayasree Sengupta, Sushmita Ruj, Sipra Das Bit
Privacy Preserving Resource Constrained Industrial Internet of Thing Secret Sharing Verifiable Learning

February 24, 2022

How reparametrization trick broke differentially-private text representation learning
Ivan Habernal
Differential Privacy Privacy Preserving NLP Community Privacy Guarantee Reparametrization Trick

February 16, 2022

SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Service
Songlei Wang, Yifeng Zheng, Xiaohua Jia
Scientific Inference Privacy Preserving Cloud Computing GNN Training Secure Deep

February 15, 2022

Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation
Jamie Cui, Chaochao Chen, Lingjuan Lyu, Carl Yang, Li Wang
Privacy Preserving Sparse Data Social Recommendation Sparse Matrix Multiplication

February 9, 2022

FedQAS: Privacy-aware machine reading comprehension with federated learning
Addi Ait-Mlouk, Sadi Alawadi, Salman Toor, Andreas Hellander
Question Answering Language Understanding Privacy Preserving Private Data Machine Reading Comprehension

February 8, 2022

APPFL: Open-Source Software Framework for Privacy-Preserving Federated Learning
Minseok Ryu, Youngdae Kim, Kibaek Kim, Ravi K. Madduri
Federated Learning Privacy Preserving Federated Learning Framework Open Source Framework

February 7, 2022

ABG: A Multi-Party Mixed Protocol Framework for Privacy-Preserving Cooperative Learning
Hao Wang, Zhi Li, Chunpeng Ge, Willy Susilo
Privacy Preserving Parameter Sharing Privacy Preserving Computation Cooperative Learning Party Protocol

February 1, 2022

Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs
Hongwei Jin, Xun Chen
Privacy Preserving Graph Learning Graph Structure Local Differential Privacy Graph Kernel Gromov Wasserstein

January 31, 2022

Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training
Shenglai Zeng, Zonghang Li, Hongfang Yu, Yihong He, Zenglin Xu, Dusit Niyato, Han Yu
Training Data Privacy Preserving Group Setting Heterogeneous Federated Learning Unobserved Heterogeneity

January 29, 2022

Challenges and approaches to privacy preserving post-click conversion prediction
Conor O'Brien, Arvind Thiagarajan, Sourav Das, Rafael Barreto, Chetan Verma, Tim Hsu, James Neufield, Jonathan J Hunt
Technical Challenge Constructive Approach Privacy Preserving User Privacy Post Click

January 20, 2022

Caring Without Sharing: A Federated Learning Crowdsensing Framework for Diversifying Representation of Cities
Michael Cho, Afra Mashhadi
Privacy Preserving Urban Environment Sharing Matter Movable Obstacle CaRE SD Mobile Crowdsensing Representation Diversity

January 17, 2022

Fairness in Federated Learning for Spatial-Temporal Applications
Afra Mashhadi, Alex Kyllo, Reza M. Parizi
Procedural Fairness Spatio Temporal Privacy Preserving Large Network

January 13, 2022

Towards a Data Privacy-Predictive Performance Trade-off
Tânia Carvalho, Nuno Moniz, Pedro Faria, Luís Antunes
Raw Data Privacy Preserving Predictive Performance Data Privacy Private Prediction Identification Risk

January 8, 2022

December 21, 2021

Synthetic Data and Simulators for Recommendation Systems: Current State and Future Directions
Adam Lesnikowski, Gabriel de Souza Pereira Moreira, Sara Rabhi, Karl Byleen-Higley
Synthetic Data Privacy Preserving Recommendation System Future Direction Interactive Simulation Real Data Current State Data Fidelity

December 15, 2021

December 14, 2021

Birds Eye View Social Distancing Analysis System
Zhengye Yang, Mingfei Sun, Hongzhe Ye, Zihao Xiong, Gil Zussman, Zoran Kostic
Privacy Preserving Social Distancing

Privacy Preserving

Papers

SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning

SPRITE: A Scalable Privacy-Preserving and Verifiable Collaborative Learning for Industrial IoT

How reparametrization trick broke differentially-private text representation learning

SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Service

Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation

FedQAS: Privacy-aware machine reading comprehension with federated learning

APPFL: Open-Source Software Framework for Privacy-Preserving Federated Learning

ABG: A Multi-Party Mixed Protocol Framework for Privacy-Preserving Cooperative Learning

Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs

Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training

Challenges and approaches to privacy preserving post-click conversion prediction

Caring Without Sharing: A Federated Learning Crowdsensing Framework for Diversifying Representation of Cities

Fairness in Federated Learning for Spatial-Temporal Applications

Towards a Data Privacy-Predictive Performance Trade-off

LoMar: A Local Defense Against Poisoning Attack on Federated Learning

ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems

Synthetic Data and Simulators for Recommendation Systems: Current State and Future Directions

One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks

HyObscure: Hybrid Obscuring for Privacy-Preserving Data Publishing

Birds Eye View Social Distancing Analysis System