Data Privacy

Data privacy research focuses on developing methods to protect sensitive information during data collection, processing, and analysis, particularly within machine learning applications. Current research emphasizes techniques like differential privacy, federated learning, and homomorphic encryption, often implemented using neural networks, large language models, and generative adversarial networks, to mitigate privacy risks while maintaining data utility. This field is crucial for responsible AI development, impacting various sectors by enabling privacy-preserving data sharing and analysis in healthcare, finance, and other sensitive domains. The ongoing development of robust privacy-preserving techniques is essential for building trust and ensuring ethical use of data-driven technologies.

Papers

February 14, 2022

Regional Differences in Information Privacy Concerns After the Facebook-Cambridge Analytica Data Scandal
Felipe González-Pizarro, Andrea Figueroa, Claudia López, Cecilia Aragon
Data Privacy Multiple Source Privacy Framework Privacy Concern

February 2, 2022

Detecting Privacy Requirements from User Stories with NLP Transfer Learning Models
Francesco Casillo, Vincenzo Deufemia, Carmine Gravino
Natural Language Processing Transfer Learning Data Privacy Privacy Sensitive Requirement Engineering User Story

January 27, 2022

Efficiently Maintaining Next Basket Recommendations under Additions and Deletions of Baskets and Items
Benjamin Longxiang Wang, Sebastian Schelter
Recommender System Data Privacy Sequential Recommender System Item Popularity Long Form Deletion Basket Recommendation Basket Sequence

January 24, 2022

Federated Unlearning with Knowledge Distillation
Chen Wu, Sencun Zhu, Prasenjit Mitra
Knowledge Distillation Training Data Backdoor Attack Data Privacy Federated Unlearning

January 18, 2022

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

November 10, 2021

Lightweight machine unlearning in neural network
Kongyang Chen, Yiwen Wang, Yao Huang
Neural Network Incremental Learning Machine Unlearning Memory Trace Data Privacy

September 13, 2021

Training Fair Models in Federated Learning without Data Privacy Infringement
Xin Che, Jingdi Hu, Zirui Zhou, Yong Zhang, Lingyang Chu
Procedural Fairness Private Data Fair Machine Learning Data Privacy Fair Model Fairness Analysis Copyright Infringement