Image de couverture de livre

Does Training with Synthetic Data Truly Protect Privacy?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Yunpeng, Zhang, Jie
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets
par: Ganev, Georgi, et autres
Publié: (2023)

Scalable and Privacy-Preserving Synthetic Data Generation on Decentralised Web
par: Ramesh, Vishal, et autres
Publié: (2023)

Privacy-Preserving Fair Synthetic Tabular Data
par: Sarmin, Fatima J., et autres
Publié: (2025)

Privacy Vulnerabilities in Marginals-based Synthetic Data
par: Golob, Steven, et autres
Publié: (2024)

Understanding the Impact of Data Domain Extraction on Synthetic Data Privacy
par: Ganev, Georgi, et autres
Publié: (2025)

Synthetic Data: Revisiting the Privacy-Utility Trade-off
par: Sarmin, Fatima Jahan, et autres
Publié: (2024)

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data
par: Zhou, Yan, et autres
Publié: (2025)

Training Data Reconstruction: Privacy due to Uncertainty?
par: Runkel, Christina, et autres
Publié: (2024)

Privacy Amplification Through Synthetic Data: Insights from Linear Regression
par: Pierquin, Clément, et autres
Publié: (2025)

Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy
par: Aliakbarpour, Maryam, et autres
Publié: (2024)

Machine Learning with Privacy for Protected Attributes
par: Mahloujifar, Saeed, et autres
Publié: (2025)

SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy
par: Nahid, Md Mahadi Hasan, et autres
Publié: (2024)

Private Truly-Everlasting Robust-Prediction
par: Stemmer, Uri
Publié: (2024)

SpinML: Customized Synthetic Data Generation for Private Training of Specialized ML Models
par: Zhang, Jiang, et autres
Publié: (2025)

Adaptive Backtracking for Privacy Protection in Large Language Models
par: Yao, Zhihao, et autres
Publié: (2025)

Driving Privacy Forward: Mitigating Information Leakage within Smart Vehicles through Synthetic Data Generation
par: Parikh, Krish
Publié: (2024)

Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy
par: Krüger, Fabian P., et autres
Publié: (2024)

The DCR Delusion: Measuring the Privacy Risk of Synthetic Data
par: Yao, Zexi, et autres
Publié: (2025)

Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions
par: Wu, Yihan, et autres
Publié: (2024)

Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
par: Huang, Catherine, et autres
Publié: (2024)

Robust Spectral Watermark for Synthetic Tabular Data
par: Zhao, Yizhou, et autres
Publié: (2025)

Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration
par: Zhang, Yiwei, et autres
Publié: (2025)

Evaluations of Machine Learning Privacy Defenses are Misleading
par: Aerni, Michael, et autres
Publié: (2024)

Six Levels of Privacy: A Framework for Financial Synthetic Data
par: Balch, Tucker, et autres
Publié: (2024)

KIPPS: Knowledge infusion in Privacy Preserving Synthetic Data Generation
par: Kotal, Anantaa, et autres
Publié: (2024)

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
par: Zhang, Chenxiang, et autres
Publié: (2025)

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
par: Zhou, Yvonne, et autres
Publié: (2024)

Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
par: Zhang, Jie, et autres
Publié: (2024)

Protecting Activity Sensing Data Privacy Using Hierarchical Information Dissociation
par: Wang, Guangjing, et autres
Publié: (2024)

Provable Privacy Attacks on Trained Shallow Neural Networks
par: Smorodinsky, Guy, et autres
Publié: (2024)

Privacy-Preserving 3-Layer Neural Network Training
par: Chiang, John
Publié: (2023)

Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems
par: Jin, Weifei, et autres
Publié: (2025)

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
par: Lou, Jiadong, et autres
Publié: (2025)

Learning to Attack: Uncovering Privacy Risks in Sequential Data Releases
par: Cui, Ziyao, et autres
Publié: (2025)

Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection
par: Lange, Lucas, et autres
Publié: (2024)

Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?
par: Wen, Rui, et autres
Publié: (2024)

Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemble
par: Liu, Dancheng, et autres
Publié: (2024)

Diverse Community Data for Benchmarking Data Privacy Algorithms
par: Sen, Aniruddha, et autres
Publié: (2023)

Vulnerability-Aware Robust Multimodal Adversarial Training
par: Zhang, Junrui, et autres
Publié: (2025)

Managing Correlations in Data and Privacy Demand
par: Chaudhuri, Syomantak, et autres
Publié: (2025)