隐私计算与数据要素 · 全部实体（第 7 / 100 页）

本页收录第 601–700 条，共 9951 条 · 返回 隐私计算与数据要素 首页

• CDLAKS: Chaotic DNA-Based Lightweight Authenticated Key-Dependent Steganographic Framework for Secure Transmission of Medical Images in Iot Environments
  preprints 2026 置信度 0.70
• TrustDS: A Policy‑First, Privacy‑Preserving Framework for Interoperable Data Exchange with Real‑World Validation
  preprints 2025 置信度 0.70
• Federated Fine‐Tuning of Large Language Models with Privacy Preservation and Cross‐Domain Semantic Alignment
  preprints 2025 置信度 0.70
• An Efficient and Effective Model for Preserving Sensitive Data in Location-Based Graphs Using Data Generalization and Data Suppression in Conjunction with Data Sliding Windows and R-Trees
  preprints 2025 置信度 0.67
• Investigating the fundamental characteristics of retinal age models
  Abstract Retinal age is a biological ageing marker estimated from retinal images. Its deviation from chronological age, termed the retinal age gap (RAG), has been associated with adverse health outcomes. However, fundamental characteristics of retinal age mode…
  preprints 2026 置信度 0.77 medicinepsychologyscience policycs.aineuroscience
• h5adify: neuro-symbolic metadata harmonization enables scalable AnnData integration with local large language models
  preprints 2026 置信度 0.63
• Public perceptions of spatial computing in health: Opportunities and barriers for supporting self-care and wellbeing
  preprints 2026 置信度 0.67
• PrivacyPreserveNet: A Multilevel Privacy-Preserving Framework for Multimodal LLMs via Gradient Clipping and Attention Noise
  preprints 2025 置信度 0.70
• An Efficient Differentially-Private Weighted Support Vector Machine Algorithm with Noisy Gradient Descent
  preprints 2025 置信度 0.70
• PALSYN: A Method for Synthetic Multi-Perspective Event Log Generation with Differential Private Guarantees
  preprints 2025 置信度 0.67
• Design and Evaluation of a Context-Aware Multimodal Recommendation and QA System with Retrieval-Augmented Generation
  preprints 2025 置信度 0.63
• Social contact patterns across levels of deprivation in England, and implications for infectious disease transmission
  preprints 2026 置信度 0.63
• Using face averages to measure differential accuracy for demographic groups in facial recognition
  preprints 2025 置信度 0.67
• Defogger: A Visual Analysis Approach for Data Exploration of Sensitive Data Protected by Differential Privacy.
  europepmc 2024 置信度 0.76
• Assessing the Impact of Federated Learning and Differential Privacy on Multi-centre Polyp Segmentation.
  europepmc 2024 置信度 0.76
• DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy.
  europepmc 2024 置信度 0.76
• Uldp-FL: Federated Learning with Across-Silo User-Level Differential Privacy.
  europepmc 2024 置信度 0.76
• Balancing Between Privacy and Utility for Affect Recognition Using Multitask Learning in Differential Privacy-Added Federated Learning Settings: Quantitative Study.
  europepmc 2024 置信度 0.76
• A Two-Stage Differential Privacy Scheme for Federated Learning Based on Edge Intelligence.
  europepmc 2024 置信度 0.76
• A Critical Study of Composition Algorithms in Differential Privacy
  europepmc 2023 置信度 0.73
• Multi-Stage Asynchronous Federated Learning With Adaptive Differential Privacy.
  europepmc 2024 置信度 0.76
• A clustering-based differential privacy protection algorithm for weighted social networks.
  europepmc 2024 置信度 0.76
• Differential privacy in collaborative filtering recommender systems: a review.
  europepmc 2023 置信度 0.73
• Differential Privacy Preservation for Continuous Release of Real-Time Location Data.
  europepmc 2024 置信度 0.76
• The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods.
  europepmc 2024 置信度 0.76
• Evaluation of Open-Source Tools for Differential Privacy.
  europepmc 2023 置信度 0.73
• Research on differential privacy protection method based on user tendency.
  europepmc 2023 置信度 0.73
• On the Convergence and Calibration of Deep Learning with Differential Privacy.
  europepmc 2023 置信度 0.73
• Sparsified federated learning with differential privacy for intrusion detection in VANETs based on Fisher Information Matrix.
  europepmc 2024 置信度 0.76
• Augmented Differential Privacy Framework for Data Analytics
  europepmc 2023 置信度 0.73
• Robust Fingerprint of Location Trajectories Under Differential Privacy.
  europepmc 2023 置信度 0.73
• Differential Privacy Preservation for Location Semantics.
  europepmc 2023 置信度 0.73
• A standardised differential privacy framework for epidemiological modeling with mobile phone data.
  europepmc 2023 置信度 0.73
• Corrigendum: Efficient differential privacy enabled federated learning model for detecting COVID-19 disease using chest X-ray images.
  europepmc 2024 置信度 0.76
• Differential Privacy based Cloud- Data Security Model (DP-DSM) with Deep Learning in Cloud
  europepmc 2024 置信度 0.76
• DP-SSLoRA: A privacy-preserving medical classification model combining differential privacy with self-supervised low-rank adaptation.
  europepmc 2024 置信度 0.76
• A data-driven approach to choosing privacy parameters for clinical trial data sharing under differential privacy.
  europepmc 2024 置信度 0.76
• Differential Privacy Protections in 2020 U.S. Decennial Census Data Do Not Impede Measurement of Racial and Ethnic Disparities.
  europepmc 2024 置信度 0.76
• Privacy, Please: Safeguarding Medical Data in Imaging AI Using Differential Privacy Techniques.
  europepmc Abhinav Suri, Ronald M. Summers 2024 置信度 0.76
• Application of Blockchain Technology & Integration of Differential Privacy: Issues in E-Health Domains
  europepmc 2023 置信度 0.73
• Mitigating Membership Inference in Deep Survival Analyses with Differential Privacy.
  europepmc 2023 置信度 0.73
• A standardised differential privacy framework for epidemiological modelling with mobile phone data
  europepmc 2023 置信度 0.73
• Distribution-Invariant Differential Privacy.
  europepmc 2023 置信度 0.73
• Privately vertically mining of sequential patterns based on differential privacy with high efficiency and utility.
  europepmc 2023 置信度 0.73
• LDP-GAN : Generative adversarial networks with local differential privacy for patient medical records synthesis.
  europepmc 2024 置信度 0.76
• Impacts of census differential privacy for small-area disease mapping to monitor health inequities.
  europepmc 2023 置信度 0.73
• Hierarchical Aggregation for Numerical Data under Local Differential Privacy.
  europepmc 2023 置信度 0.73
• A federated learning differential privacy algorithm for non-Gaussian heterogeneous data.
  europepmc 2023 置信度 0.73
• A Neural Approach to Spatio-Temporal Data Release with User-Level Differential Privacy.
  europepmc 2023 置信度 0.73
• Task-Specific Adaptive Differential Privacy Method for Structured Data.
  europepmc 2023 置信度 0.73
• An Efficient Differential Privacy-Based Method for Location Privacy Protection in Location-Based Services.
  europepmc 2023 置信度 0.73
• Local differential privacy protection for wearable device data.
  europepmc 2022 置信度 0.73
• Heterogeneous Graph Neural Network with Semantic-aware Differential Privacy Guarantees
  europepmc 2023 置信度 0.73
• A Communication-Efficient, Privacy-Preserving Federated Learning Algorithm Based on Two-Stage Gradient Pruning and Differentiated Differential Privacy.
  europepmc 2023 置信度 0.73
• Differential privacy protection algorithm for network sensitive information based on singular value decomposition.
  europepmc 2023 置信度 0.73
• Differential privacy preserved federated transfer learning for multi-institutional ⁶⁸Ga-PET image artefact detection and disentanglement.
  europepmc 2023 置信度 0.73
• DPCL: Constrative Representation Learning with Differential Privacy
  europepmc 2022 置信度 0.73
• Successive Trajectory Privacy Protection with Semantics Prediction Differential Privacy.
  europepmc 2022 置信度 0.73
• Differential privacy preserved federated learning for prognostic modeling in COVID-19 patients using large multi-institutional chest CT dataset.
  europepmc 2024 置信度 0.76
• Global and local impacts of differential privacy on estimates of health care inequity.
  europepmc 2022 置信度 0.73
• A federated learning differential privacy algorithm for non-Gaussian heterogeneous data
  europepmc 2022 置信度 0.73
• Differential privacy medical data publishing method based on attribute correlation.
  europepmc 2022 置信度 0.73
• DPVisCreator: Incorporating Pattern Constraints to Privacy-preserving Visualizations via Differential Privacy.
  europepmc 2023 置信度 0.73
• Differential Privacy Distributed Logistic Regression with Objective Function Perturbation
  europepmc 2022 置信度 0.73
• Generating synthetic personal health data using conditional generative adversarial networks combining with differential privacy.
  europepmc 2023 置信度 0.73
• <i>Sarve</i>: synthetic data and local differential privacy for private frequency estimation.
  europepmc 2022 置信度 0.73
• Exploring Intermediate Paradigms: A Comparative Analysis of Shuffle and Pan-Private Models in Differential Privacy with Emphasis on Trust Levels, Engineering, and Mathematical Perspectives
  europepmc 2023 置信度 0.73
• CONSISTENT SPECTRAL CLUSTERING OF NETWORK BLOCK MODELS UNDER LOCAL DIFFERENTIAL PRIVACY.
  europepmc 2022 置信度 0.73
• Personalized Sampling Graph Collection with Local Differential Privacy for Link Prediction
  europepmc 2022 置信度 0.73
• Restrictively Self-sampled and Compressed Local Differential Privacy in Federated Learning
  europepmc 2022 置信度 0.73
• Genomic Data Sharing under Dependent Local Differential Privacy.
  europepmc 2022 置信度 0.73
• Differential Privacy via Haar Wavelet Transform and Gaussian Mechanism for Range Query.
  europepmc 2022 置信度 0.73
• Differential privacy in health research: A scoping review.
  europepmc 2021 置信度 0.73
• Enhancing Data Protection in Dynamic Consent Management Systems: Formalizing Privacy and Security Definitions with Differential Privacy, Decentralization, and Zero-Knowledge Proofs.
  europepmc 2023 置信度 0.73
• Differential privacy for eye tracking with temporal correlations.
  europepmc 2021 置信度 0.73
• Analysis of Application Examples of Differential Privacy in Deep Learning.
  europepmc 2021 置信度 0.73
• ABCDP: Approximate Bayesian Computation with Differential Privacy.
  europepmc 2021 置信度 0.73
• The Discrete Gaussian Expectation Maximization (Gradient) Algorithm for Differential Privacy.
  europepmc 2021 置信度 0.73
• The effect of differential privacy on Medicaid participation among racial and ethnic minority groups.
  europepmc 2022 置信度 0.73
• Privacy-preserving Model Training for Disease Prediction Using Federated Learning with Differential Privacy.
  europepmc 2022 置信度 0.73
• A(DP) ²SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent With Differential Privacy.
  europepmc 2022 置信度 0.73
• An Efficient Location Privacy Protection Method for Location-Based Services based on Differential Privacy
  europepmc 2022 置信度 0.73
• A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning.
  europepmc 2022 置信度 0.73
• Deep Learning with Gaussian Differential Privacy.
  europepmc 2020 置信度 0.73
• Differential Privacy and the Accuracy of County-Level Net Migration Estimates.
  europepmc 2022 置信度 0.73
• On the difficulty of achieving Differential Privacy in practice: user-level guarantees in aggregate location data.
  europepmc 2022 置信度 0.73
• B-DP: Dynamic Collection and Publishing of Continuous Check-In Data with Best-Effort Differential Privacy.
  europepmc 2022 置信度 0.73
• An Uplink Communication-Efficient Approach to Featurewise Distributed Sparse Optimization With Differential Privacy.
  europepmc 2021 置信度 0.73
• Distributed Consensus Algorithms Based on Differential Privacy
  This paper investigates the design and analysis of distributed consensus algorithms incorporating differential privacy. Achieving consensus in a distributed system while simultaneously protecting the privacy of individual nodes' data presents a complex challen…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescryptography and securitycs.crcomputer sciencecomputer security
• Distributed Consensus Algorithms Based on Differential Privacy
  This paper investigates the design and analysis of distributed consensus algorithms incorporating differential privacy. Achieving consensus in a distributed system while simultaneously protecting the privacy of individual nodes' data presents a complex challen…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescryptography and securitycs.crcomputer sciencecomputer security
• Generative Modeling of Cryptographic Protocols with Differential Privacy
  This paper investigates the critical privacy concerns arising from training generative models of cryptographic protocols. Traditional generative modeling techniques, particularly Generative Adversarial Networks (GANs), can inadvertently leak sensitive informat…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescryptography and securitygenerative grammarcs.lgcs.ai
• Generative Modeling of Cryptographic Protocols with Differential Privacy
  This paper investigates the critical privacy concerns arising from training generative models of cryptographic protocols. Traditional generative modeling techniques, particularly Generative Adversarial Networks (GANs), can inadvertently leak sensitive informat…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescryptography and securitygenerative grammarcs.lgcs.ai
• Algorithmic Fairness via Differential Privacy and Representation Learning
  Algorithmic fairness has emerged as a critical concern in the development and deployment of machine learning systems. Traditional approaches to fairness often involve post-processing techniques or modifying the training data, which can negatively impact model …
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescomputer scienceartificial intelligencecs.lgcryptography and security
• Algorithmic Fairness via Differential Privacy and Representation Learning
  Algorithmic fairness has emerged as a critical concern in the development and deployment of machine learning systems. Traditional approaches to fairness often involve post-processing techniques or modifying the training data, which can negatively impact model …
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescomputer scienceartificial intelligencecs.lgcryptography and security
• Differential Privacy with Stochastic Gradient Descent via Optimal Transport
  This paper introduces a novel approach to achieving differential privacy within stochastic gradient descent (SGD) by leveraging the principles of optimal transport. Existing methods often struggle to balance privacy guarantees with model accuracy, frequently r…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescs.lgcryptography and securitycomputer sciencestat.ml
• Differential Privacy with Stochastic Gradient Descent via Optimal Transport
  This paper introduces a novel approach to achieving differential privacy within stochastic gradient descent (SGD) by leveraging the principles of optimal transport. Existing methods often struggle to balance privacy guarantees with model accuracy, frequently r…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescs.lgcryptography and securitycomputer sciencestat.ml
• Quantum-Enhanced Differential Privacy for Graph Data
  This paper investigates the application of quantum error correction (QEC) to enhance differential privacy (DP) for graph data. Traditional DP mechanisms, when applied to graph datasets, often result in substantial utility loss due to the inherent structure and…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer sciencecomputer and information sciencescryptography and securitycs.aics.lg
• Quantum-Enhanced Differential Privacy for Graph Data
  This paper investigates the application of quantum error correction (QEC) to enhance differential privacy (DP) for graph data. Traditional DP mechanisms, when applied to graph datasets, often result in substantial utility loss due to the inherent structure and…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer sciencecomputer and information sciencescryptography and securitycs.aics.lg
• Causal Discovery via Latent Variable Interventions with Differential Privacy
  This paper introduces a novel approach to causal discovery that integrates latent variable interventions with differential privacy. Existing causal discovery algorithms often suffer from biases introduced by observational data and lack adequate protection agai…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescs.aicryptography and securitycs.lgelectrical engineering, electronic engineering, information engineering
• Causal Discovery via Latent Variable Interventions with Differential Privacy
  This paper introduces a novel approach to causal discovery that integrates latent variable interventions with differential privacy. Existing causal discovery algorithms often suffer from biases introduced by observational data and lack adequate protection agai…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescs.aicryptography and securitycs.lgelectrical engineering, electronic engineering, information engineering