隐私计算与数据要素 · 全部实体（第 88 / 100 页）

本页收录第 8701–8800 条，共 10000 条 · 返回 隐私计算与数据要素 首页

• Gradient Methods for Federated Optimization
  crossref Alexander Jung 2026-01-02T02:23:44Z 置信度 0.70
• Dynamic Middleware for Interoperable Federated Learning: Enabling Cross-Framework Communication
  crossref Mohammed AlKaldi, Abdullah AlShehri 2025-01-21T18:22:35Z 置信度 0.70
• Federated-survival: A Federated Learning Framework for Privacy-Preserving Survival Analysis
  Federated Learning (FL) has emerged as a promising paradigm for collaborative, privacy-conscious model training; however, its application to survival analysis remains at an early stage of development. A significant barrier to progress in this domain is the abs…
  crossref wenjun wang, Wang Hong, zhuan zhang 2026-02-11T11:38:35Z 置信度 0.70
• A roadmap for federated learning adoption
  crossref Shashank Semwal, Chandra Prakash, Bijesh Dhyani 2026-03-25T15:39:21Z 置信度 0.70
• Table 1: Federated deep learning classifier parameter setting.
  crossref 2024-12-13T05:39:34Z 置信度 0.70
• Privacy-Preserving Genomic Classification: A Blockchain-Based Federated Learning Approach
  crossref Reza Nourmohammadi, Kaiwen Zhang 2026-07-29T19:12:59Z 置信度 0.70
• Introduction to Federated Learning
  crossref Shui Yu, Lei Cui 2023-03-26T21:30:41Z 置信度 0.70
• Fundamentals of Blockchain and Federated Learning
  crossref Komal Rahul Pardeshi, Anita Mukund Pujar, Yang Li 2025-08-01T12:15:01Z 置信度 0.70
• Eleven quick tips for Biomedical Federated Learning.
  Modern statistical and machine learning techniques are effective at describing, testing hypotheses and making predictions from complex data. This effectiveness is strongly influenced by the volume and heterogeneity of available data. In many fields, including …
  pubmed Ellrott K, Malladi VS, Bélisle-Pipon JC, Demir E 等 2026 置信度 0.82
• Decentralized Federated Learning by Partial Message Exchange.
  Decentralized federated learning (DFL) has emerged as a transformative server-free paradigm that enables collaborative learning over large-scale heterogeneous networks. However, it continues to face fundamental challenges, including data heterogeneity, restric…
  pubmed Sha S, Zhou S, Wang X, Kong L 等 2026 置信度 0.82
• Differential Privacy Synthetic Tabular Data Generation for Federated Learning
  Machine learning in healthcare struggles for one main reason: good data is hard to come by. Medical records are sensitive, and the rules on sharing them between hospitals are strict. A common workaround is synthetic data, that is artificial records that copy t…
  europepmc Mariona Almató-Baucells, Carla Lázaro, Cecilio Angulo 2026 置信度 0.80
• Privacy-Preserving and Poisoning-Robust Federated Learning for Industrial IoT.
  With the rapid development of Industrial Internet of Things (IIoT), large amounts of sensor data generated by industrial devices and edge nodes have become the basis of intelligent manufacturing applications. Collaborative modeling on these distributed data is…
  pubmed Yin H, Chen C, Zhang J, Yu D 等 2026 置信度 0.82
• Multi-FedLinks: Highly reliable decentralized multibiometric federated learning links.
  In recent years, the recognition accuracies of deep learning-based biometric recognition methods, which rely on large amounts of biometric data for training, have significantly increased. However, in practical applications, biometric data are often distributed…
  pubmed Guo J, Mu H, Ren H, Han C 等 2026 置信度 0.82
• Optimal Transport-Based Heterogeneous Federated Learning for Chest X-Rays.
  In some federated learning (FL) scenarios, discrepancies in local client devices result in inconsistent image resolutions, which motivates clients to adopt models with different depths and widths. Existing heterogeneous federated learning methods struggle to m…
  pubmed Liu Y, Wang H, Qian X, Wan J 等 2026 置信度 0.82
• A Lightweight Anonymous Authentication Scheme for Federated Learning
  Abstract Federated learning enables collaborative model training between central servers and distributed clients without collecting users’ raw sensitive data, which effectively promotes the large-scale deployment of intelligent collaborative services. Consider…
  europepmc Shu Wu, Guoqiang Meng, Linlin Lu, Xiaojuan Dong 等 2026 置信度 0.80
• EPDA: An Efficient and Privacy-preserving Dual Aggregation Scheme for Federated Learning in VANETs
  Abstract Federated Learning (FL) enables devices to collaboratively train models without sharing raw data, but attackers can still infer sensitive information from uploaded updates. Existing cryptographic methods provide security but often lack essential priva…
  europepmc Yifeng Zhao, Qingqing Xie 2026 置信度 0.80
• ToPPFed: Topological Prototype-Enhanced Personalized Federated Learning for Neuropsychiatric Disorders Identification.
  Functional connectivity networks (FCNs) derived from functional magnetic resonance imaging (fMRI) have been widely used to characterize topological alterations of brain networks in neuropsychiatric disorders (NDs). Given the frequent restrictions on direct mul…
  pubmed Zheng Y, Jia Z, Guan Z, Chen Y 等 2026 置信度 0.82
• Evaluating federated learning approaches for mammography under breast density heterogeneity.
  Breast density is a key factor that influences mammography interpretation and is a major source of heterogeneity in multicenter datasets. Such heterogeneity poses challenges for collaborative machine learning across institutions, particularly in federated lear…
  pubmed Quintana GI, Di Maria FM, Vancamberg L 2026 置信度 0.82
• Federated Learning Framework with Differential Privacy over Homomorphic Vector Encryption for Data-Sensitive Applications
  Abstract Federated Learning (FL) has become a popular paradigm in recent years, attributed to its concept of insight sharing for ensuring data privacy. It has been found to be of extensive utility in applications that regularly deal with confiden-tial data and…
  europepmc Manu Narula, Jasraj Meena, Dinesh Vishwakarma 2026 置信度 0.80
• A Method for Workout Video Classification via Explainable and Federated Learning.
  In recent years, the widespread availability of wearable devices and smartphones has enabled the large-scale collection of human activity data, fostering new opportunities for automatic workout recognition and personalized fitness monitoring. However, the cent…
  pubmed Ciardiello L, Agnello P, Petyx M, Martinelli F 等 2026 置信度 0.82
• Privacy-Preserving Federated Learning for Building Energy Forecasting: A Differential Privacy Analysis of Aggregation Strategies
  europepmc 2026 置信度 0.80
• Federated learning for privacy-preserving ophthalmic artificial intelligence: clinical applications and translational challenges.
  Federated learning (FL) is increasingly relevant to ophthalmology because retinal photographs, optical coherence tomography (OCT), OCT angiography, visual fields, and linked clinical records are clinically valuable but difficult to pool across institutions. In…
  pubmed Wei Y, Zhao K, Grzybowski A, Jin K 2026 置信度 0.82
• MoFedAGR: Mitigating client drift with adaptive gradient regularization and global momentum in federated learning.
  Federated learning is a novel distributed machine learning framework with privacy-protection, yet it is vulnerable to the effects of heterogeneous data. Heterogeneous data drive client models that overfit local datasets and depart from the global optimum durin…
  pubmed Wang X, Tian L, Gan J, Yang C 等 2026 置信度 0.82
• Federated learning for MRI-based BrainAGE: A multicenter study on post-stroke functional outcome prediction.
  Brain-predicted age difference (BrainAGE) is a neuroimaging biomarker reflecting brain health, with potential implications for post-stroke recovery. However, training robust BrainAGE models requires large, diverse datasets, often restricted by privacy and regu…
  pubmed Roca V, Tommasi M, Andrey P, Bellet A 等 2026 置信度 0.82
• DBST-FL: Dynamic Behavioural and Semantic Trust for Robust Federated Learning in Industrial IoT.
  Federated learning (FL) has emerged as an effective paradigm for collaborative model training in Industrial Internet of Things (IIoT) environments by enabling distributed devices to learn shared models without exchanging raw data. However, existing FL defence …
  pubmed Alazab A, Tom AK, Jan T, Whaiduzzaman M 等 2026 置信度 0.82
• SCKM: Symmetric Co-Skew Moment for User Selection in Federated Learning.
  We introduce the symmetric co-skewness moment (SCKM)-a third-order informational dissimilarity metric that consistently outperforms state-of-the-art client-selection heuristics in federated learning (FL) under heterogeneous data. Unlike similarity-driven schem…
  pubmed Li L, Liu Y, Ning Y, Rini S 等 2026 置信度 0.82
• Enhanced Spectral Clustering Robust Aggregation for Lens Detection in Federated Learning Against Byzantine Attacks.
  Although federated learning (FL) addresses the issues of centralized data storage and privacy leakage, its distributed nature makes it vulnerable to malicious clients. These malicious participants introduce malicious parameters during the training procedure, w…
  pubmed Bai F, Jin B, Zeng K, Shen T 等 2026 置信度 0.82
• Federated learning for heterogeneous edge environments_ A multi-domain evaluation on object detection and energy forecasting
  europepmc 2026 置信度 0.80
• Closed-Form Federated Learning Without Client Labels Through Federated Semi-Supervised Learning
  Federated semi-supervised learning (FSSL) in the labels-at-server setting is governed by dual label shift: class priors vary across clients, and the server's labeled distribution differs from the clients' unlabeled data. Gradient-based method…
  crossref Jihyung Choi, Seoung Bum Kim 2026-08-21T18:46:17Z 置信度 0.70
• Differential Privacy
  A robust yet accessible introduction to the idea, history, and key applications of differential privacy—the gold standard of algorithmic privacy protection. Differential privacy (DP) is an increasingly popular, though controversial, approach to protecting per…
  semanticscholar S. Garfinkel, Simson L. Garfinkel 2025-03-25 置信度 0.74
• Persistence Landscapes Across Privacy Budgets for Explanation Methods Across Differential Privacy Mechanisms
  Abstract Machine-learning credit scoring must be both auditable and privacy-preserving, yet post-hoc explainers may rely on sensitive records or privileged model access that privacy constraints restrict. We study how local explanations for a feed-forward neura…
  europepmc Paul Zheng 2026 置信度 0.80
• Privacy-Preserving Multidimensional Data Analysis : Query Answering and Data Publication under Differential Privacy
  Analyse de données multidimensionnelles préservant la confidentialité : réponse aux requêtes et publication de données sous garanties de la Differential Privacy Dans le monde moderne, presque chaque individu dépend et interagit quotidiennement avec de multiple…
  crossref Ala Eddine Laouir 2026-04-09T12:11:16Z 置信度 0.70
• Research a New Tradeoff Method Between Privacy and Utility in Differential privacy
  Abstract The solution of the contradiction between privacy protection and data utility is a research hotspot in the field of privacy protection. Aiming at the problem of tradeoff between privacy and utility in the scenario of differential privacy offline data …
  europepmc panjun sun 2021 置信度 0.80
• Preliminary of Differential Privacy
  crossref Tianqing Zhu, Gang Li, Wanlei Zhou, Philip S. Yu 2017-08-22T09:03:04Z 置信度 0.70
• Differential Privacy in Energy Systems
  crossref James Anderson, Fengyu Zhou, Steven H. Low 2026-08-04T15:34:34Z 置信度 0.70
• Local Differential Privacy for Data Clustering
  crossref Lisa Bruder, Mina Alishahi 2024-07-12T19:48:20Z 置信度 0.70
• Differential Privacy for Distributed Traffic Monitoring in Smart Cities
  crossref Marcus Gelderie, Maximilian Luff, Lukas Brodschelm 2024-03-01T18:44:53Z 置信度 0.70
• Differential Privacy and Medical Data Analysis
  crossref Vinith M. Suriyakumar, Nicolas Papernot, Anna Goldenberg 2026-08-04T15:34:34Z 置信度 0.70
• Differential Privacy for Location-Based Systems
  crossref 2025-01-10T20:06:00Z 置信度 0.70
• Multi-tier Privacy Protection for Large Language Models using Differential Privacy
  The increasing integration of machine learning models into sensitive domains such as healthcare, finance, and government services has amplified concerns surrounding data privacy and the protection of personal information. A novel multi-tier differential privac…
  europepmc Dominic Novado, Eliyah Cohen, Jacob Foster 2024 置信度 0.80
• Per-instance Differential Privacy
  We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard DP and inherits all…
  crossref Yu-Xiang Wang 2019-04-01T02:10:17Z 置信度 0.70
• WebGPU Accelerated Client-Side AI for Privacy Preserving Dermatological Diagnostics: Performance Benchmarking and Local Differential Privacy Integration
  crossref Arpankumar Patel 2026-02-23T11:45:47Z 置信度 0.70
• DIFFERENTIAL PRIVACY AND HOMOMORPHIC ENCRYPTION–BASED PRIVACY-PRESERVING ENSEMBLE LEARNING FOR MEDICAL DIAGNOSIS
  Machine learning in healthcare is increasingly being used for disease diagnosis, prognosis and patient care. But medical data are also sensitive, and the exposure of such personal health information by unauthorized access or model inference is a serious concer…
  crossref 2025-12-29T12:21:06Z 置信度 0.70
• Human Action Image Generation With Differential Privacy
  crossref Qing Wang 2022-06-17T00:45:11Z 置信度 0.70
• Differential Privacy: A Primer
  Differential Privacy (DP) is a mathematical framework that protects individual privacy in data analysis while allowing useful insights to be extracted. It works by adding carefully calibrated noise to data or query results, ensuring that including or excluding…
  crossref Abhishek Tiwari 2024-10-31T18:43:18Z 置信度 0.70
• Differential Privacy with Semantic Neighboring: A Notion of Privacy for Personalization Services
  Many internet services are personalized to the interests of users. The personalization is usually based on the user profiles extracted from the interactions of users with internet applications. The profile, however, may naturally reveal private information abo…
  crossref Ehsan Edalat, Mehran S. Fallah 2025-01-20T09:31:17Z 置信度 0.70
• Transparent Privacy is Principled Privacy
  crossref Ruobin Gong 2022-07-11T14:30:51Z 置信度 0.70
• Concepts and Theories
  crossref 2025-03-25T16:46:09Z 置信度 0.70
• Differential Privacy
  crossref Balázs Pejó, Damien Desfontaines 2022-04-09T12:02:46Z 置信度 0.70
• Review of: "SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy"
  crossref Andrey Makrushin 2025-03-05T14:39:52Z 置信度 0.70
• Privacy-Preserving Smart Metering through Data Synthesis and Differential Privacy
  Smart meters (SM) have generated vast amounts of detailed load data, enabling advanced load profile analyses that can significantly enhance smart grid efficiency. However, this data collection raises serious privacy concerns, as it can inadvertently expose sen…
  crossref Zakia Zaman, Praveen Gauravaram, Sanjay Jha, Wen Hu 2024-09-23T10:09:25Z 置信度 0.70
• Differential Privacy “Working Towards Differential Privacy for Sensitive Text “
  The differential-privacy idea states that maintaining privacy often includes adding noise to a data set to make it more challenging to identify data that corresponds to specific individuals. The accuracy of data analysis is typically decreased when noise is ad…
  crossref Mohammad Naeem Kanyar 2023-06-08T12:08:47Z 置信度 0.70
• Review of: "SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy"
  crossref Karima Makhlouf 2025-03-06T02:23:41Z 置信度 0.70
• Minimaxity, Statistical Thinking and Differential Privacy
  We discuss the role of minimax statistical theory for privacy theory. Minimax theory gives a way to measure information loss for sanitized databases. We also discuss some differences between privacy theory from the statistical perspective versus the computer s…
  crossref Larry Wasserman 2018-02-27T14:38:30Z 置信度 0.70
• Review of: "SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy"
  crossref Bhavani Malisetty 2025-02-13T11:31:32Z 置信度 0.70
• Federated Learning Harnessed with Differential Privacy for Heart Disease Prediction: Enhancing Privacy and Accuracy
  crossref Wided Moulahi, Tarek Moulahi, Imen Jdey, Salah Zidi 2025-02-28T12:43:20Z 置信度 0.70
• Review of: "SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy"
  crossref Anand Vunnam 2025-02-17T08:56:56Z 置信度 0.70
• Review for "Protecting health monitoring privacy in fitness training: A federated learning framework based on personalized differential privacy"
  crossref 2024-05-01T09:59:27Z 置信度 0.70
• Dual Privacy Protection in Financial AI: When k-Anonymity and Differential Privacy Improve Accuracy Together
  crossref Kenzo Arai 2026-01-05T20:07:06Z 置信度 0.70
• Review of: "SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy"
  crossref Weisan Wu 2025-02-09T07:28:31Z 置信度 0.70
• Deep Learning with Differential Privacy
  Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information. The models s…
  semanticscholar Martín Abadi, Andy Chu, I. Goodfellow, H. B. McMahan 等 2016-07-01 置信度 0.74 Conference on Computer and Communications Security
• The Algorithmic Foundations of Differential Privacy
  semanticscholar C. Dwork, Aaron Roth 2014-08-11 置信度 0.74 Foundations and Trends® in Theoretical Computer Science
• Differential Privacy
  semanticscholar C. Dwork 2006-07-10 置信度 0.74 International Colloquium on Automata, Languages and Programming
• Differential Privacy: A Survey of Results
  semanticscholar C. Dwork 2008-04-25 置信度 0.74 Theory and Applications of Models of Computation
• Federated Learning With Differential Privacy: Algorithms and Performance Analysis
  Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients’ private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from cl…
  semanticscholar Kang Wei, Jun Li, Ming Ding, Chuan Ma 等 2019-11-01 置信度 0.74 IEEE Transactions on Information Forensics and Security
• Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity.
  europepmc 2025 置信度 0.80
• Privacy and Fairness Analysis in the Post-Processed Differential Privacy Framework
  The post-processed Differential Privacy (DP) framework has been routinely adopted to preserve privacy while maintaining important invariant characteristics of datasets in data-release applications such as census data. Typical invariant characteristics include …
  semanticscholar Ying Zhao, Kai Zhang, Longxiang Gao, Jinjun Chen 2025 置信度 0.74 IEEE Transactions on Information Forensics and Security
• Rényi Differential Privacy
  We propose a natural relaxation of differential privacy based on the Rényi divergence. Closely related notions have appeared in several recent papers that analyzed composition of differentially private mechanisms. We argue that the useful analytical tool can b…
  semanticscholar Ilya Mironov 2017-02-24 置信度 0.74 IEEE Computer Security Foundations Symposium
• Clustered Federated Learning With Adaptive Local Differential Privacy on Heterogeneous IoT Data
  The Internet of Things (IoT) is penetrating many aspects of our daily life with the proliferation of artificial intelligence applications. Federated learning (FL) has emerged as a promising paradigm enabling many intelligent IoT applications; however, the tran…
  semanticscholar Zaobo He, Lintao Wang, Zhipeng Cai 2024-01-01 置信度 0.74 IEEE Internet of Things Journal
• How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
  Machine Learning (ML) models are ubiquitous in real-world applications and are a constant focus of research. Modern ML models have become more complex, deeper, and harder to reason about. At the same time, the community has started to realize the importance of…
  semanticscholar N. Ponomareva, Hussein Hazimeh, Alexey Kurakin, Zheng Xu 等 2023-03-01 置信度 0.74 Journal of Artificial Intelligence Research
• Differential Privacy in Distributed Optimization With Gradient Tracking
  Optimization with gradient tracking is particularly notable for its superior convergence results among the various distributed algorithms, especially in the context of directed graphs. However, privacy concerns arise when gradient information is transmitted di…
  semanticscholar Lingying Huang, Junfeng Wu, Dawei Shi, S. Dey 等 2024-09-01 置信度 0.74 IEEE Transactions on Automatic Control
• Tensor Recurrent Neural Network With Differential Privacy
  Recurrent neural network (RNN), a branch of deep learning, is a powerful model for sequential data that has outstanding performance on a wide range of important Internet of Things (IoT) tasks. This unprecedented growth of RNN model has however encountered both…
  semanticscholar Jun Feng, L. Yang, Bocheng Ren, Deqing Zou 等 2024-03-01 置信度 0.74 IEEE transactions on computers
• Privacy-Preserving Retrieval Augmented Generation with Differential Privacy
  With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose, retrieval-augmented generation (RAG) …
  semanticscholar Tatsuki Koga, Ruihan Wu, Kamalika Chaudhuri 2024-12-06 置信度 0.74 arXiv.org
• Opacus: User-Friendly Differential Privacy Library in PyTorch
  We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus.ai). Opacus is designed for simplicity, flexibility, and speed. It provides a simple and user-friendly API, and enables machi…
  semanticscholar Ashkan Yousefpour, I. Shilov, Alexandre Sablayrolles, Davide Testuggine 等 2021-09-25 置信度 0.74 arXiv.org
• Scenario-based Adaptations of Differential Privacy: A Technical Survey
  Differential privacy has been a de facto privacy standard in defining privacy and handling privacy preservation. It has had great success in scenarios of local data privacy and statistical dataset privacy. As a primitive definition, standard differential priva…
  semanticscholar Ying Zhao, Jia Tina Du, Jinjun Chen 2024-03-05 置信度 0.74 ACM Computing Surveys
• Rao Differential Privacy
  Differential privacy (DP) has recently emerged as a definition of privacy to release private estimates. DP calibrates noise to be on the order of an individuals contribution. Due to the this calibration a private estimate obscures any individual while preservi…
  semanticscholar Carlos Soto 2025-08-23 置信度 0.74 arXiv.org
• Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
  "Concentrated differential privacy" was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many privacy-preserving computations. We present an alternative formulation of the concept of concentra…
  semanticscholar Mark Bun, T. Steinke 2016-05-06 置信度 0.74 Theory of Cryptography Conference
• Differential Privacy for Deep and Federated Learning: A Survey
  Users’ privacy is vulnerable at all stages of the deep learning process. Sensitive information of users may be disclosed during data collection, during training, or even after releasing the trained learning model. Differential privacy (DP) is one of the main a…
  semanticscholar Ahmed El Ouadrhiri, Ahmed M Abdelhadi 2022 置信度 0.74 IEEE Access
• Certified Robustness to Adversarial Examples with Differential Privacy
  Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past defenses are best effort and have been sho…
  semanticscholar Mathias Lécuyer, Vaggelis Atlidakis, Roxana Geambasu, Daniel J. Hsu 等 2018-02-09 置信度 0.74 IEEE Symposium on Security and Privacy
• A Survey on Differential Privacy for Unstructured Data Content
  Huge amounts of unstructured data including image, video, audio, and text are ubiquitously generated and shared, and it is a challenge to protect sensitive personal information in them, such as human faces, voiceprints, and authorships. Differential privacy is…
  semanticscholar Ying Zhao, Jinjun Chen 2022-01-06 置信度 0.74 ACM Computing Surveys
• PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees
  semanticscholar James Jordon, Jinsung Yoon, M. Schaar 2018-09-27 置信度 0.74 International Conference on Learning Representations
• Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe
  Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a formal privacy guarantee, such as differential pr…
  semanticscholar Xiang Yue, Huseyin A. Inan, Xuechen Li, Girish Kumar 等 2022-10-25 置信度 0.74 Annual Meeting of the Association for Computational Linguistics
• Dynamic Personalized Federated Learning with Adaptive Differential Privacy
  Personalized federated learning with differential privacy has been considered a feasible solution to address non-IID distribution of data and privacy leakage risks. However, current personalized federated learning methods suffer from inflexible personalization…
  semanticscholar Xiyuan Yang, Wenke Huang, Mang Ye 2023 置信度 0.74 Neural Information Processing Systems
• Personalized Federated Learning With Differential Privacy and Convergence Guarantee
  Personalized federated learning (PFL), as a novel federated learning (FL) paradigm, is capable of generating personalized models for heterogenous clients. Combined with a meta-learning mechanism, PFL can further improve the convergence performance with few-sho…
  semanticscholar Kang Wei, Jun Li, Chuan Ma, Ming Ding 等 2023 置信度 0.74 IEEE Transactions on Information Forensics and Security
• Applications of Differential Privacy in Social Network Analysis: A Survey
  Differential privacy provides strong privacy preservation guarantee in information sharing. As social network analysis has been enjoying many applications, it opens a new arena for applications of differential privacy. This article presents a comprehensive sur…
  semanticscholar Honglu Jiang, J. Pei, Dongxiao Yu, Jiguo Yu 等 2023-01-01 置信度 0.74 IEEE Transactions on Knowledge and Data Engineering
• Federated Learning of Gboard Language Models with Differential Privacy
  We train and deploy language models (LMs) with federated learning (FL) and differential privacy (DP) in Google Keyboard (Gboard). The recent DP-Follow the Regularized Leader (DP-FTRL) algorithm is applied to achieve meaningfully formal DP guarantees without re…
  semanticscholar Zheng Xu, Yanxiang Zhang, Galen Andrew, Christopher A. Choquette-Choo 等 2023-05-29 置信度 0.74 Annual Meeting of the Association for Computational Linguistics
• Numerical Composition of Differential Privacy
  We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of \emph{privacy loss random variables} to quantify the privacy loss of DP algorithms.The runnin…
  semanticscholar Sivakanth Gopi, Y. Lee, Lukas Wutschitz, Yin Tat Lee 2021-06-05 置信度 0.74 Neural Information Processing Systems
• Deep Learning with Label Differential Privacy
  The Randomized Response (RR) algorithm is a classical technique to improve robustness in survey aggregation, and has been widely adopted in applications with differential privacy guarantees. We propose a novel algorithm, Randomized Response with Prior (RRWithP…
  semanticscholar Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi 等 2021-02-11 置信度 0.74 Neural Information Processing Systems
• A Robust Game-Theoretical Federated Learning Framework With Joint Differential Privacy
  Federated learning is a promising distributed machine learning paradigm that has been playing a significant role in providing privacy-preserving learning solutions. However, alongside all its achievements, there are also limitations. First, traditional framewo…
  semanticscholar Lefeng Zhang, Tianqing Zhu, P. Xiong, Wanlei Zhou 等 2023-04-01 置信度 0.74 IEEE Transactions on Knowledge and Data Engineering
• Privacy-Preserving Federated Learning for Industrial Edge Computing via Hybrid Differential Privacy and Adaptive Compression
  With the continuous improvement of hardware computing power, edge computing of industrial data has been gradually applied. In the past decade, the promotion of edge computing has also greatly improved the efficiency of industrial production. Compared with the …
  semanticscholar Bin Jiang, Jianqiang Li, Huihui Wang, H. Song 2023-02-01 置信度 0.74 IEEE Transactions on Industrial Informatics
• Exploring Homomorphic Encryption and Differential Privacy Techniques towards Secure Federated Learning Paradigm
  The trend of the next generation of the internet has already been scrutinized by top analytics enterprises. According to Gartner investigations, it is predicted that, by 2024, 75% of the global population will have their personal data covered under privacy reg…
  semanticscholar Rezak Aziz, S. Banerjee, S. Bouzefrane, Thinh Le Vinh 2023-09-13 置信度 0.74 Future Internet
• Geo-indistinguishability: differential privacy for location-based systems
  The growing popularity of location-based systems, allowing unknown/untrusted servers to easily collect huge amounts of information regarding users' location, has recently started raising serious privacy concerns. In this paper we introduce geoind, a formal not…
  semanticscholar Miguel E. Andrés, N. E. Bordenabe, K. Chatzikokolakis, C. Palamidessi 2012-12-09 置信度 0.74 Conference on Computer and Communications Security
• Blockchain-Enabled Federated Learning Data Protection Aggregation Scheme With Differential Privacy and Homomorphic Encryption in IIoT
  With rapid growth in data volume generated from different industrial devices in IoT, the protection for sensitive and private data in data sharing has become crucial. At present, federated learning for data security has arisen, and it can solve the security co…
  semanticscholar Bin Jia, Xiaosong Zhang, Jiewen Liu, Y. Zhang 等 2021-06-08 置信度 0.74 IEEE Transactions on Industrial Informatics
• What Are the Chances? Explaining the Epsilon Parameter in Differential Privacy
  Differential privacy (DP) is a mathematical privacy notion increasingly deployed across government and industry. With DP, privacy protections are probabilistic: they are bounded by the privacy budget parameter, $\epsilon$. Prior work in health and computationa…
  semanticscholar P. Nanayakkara, Mary Anne Smart, Rachel Cummings, Gabriel Kaptchuk 等 2023-03-01 置信度 0.74 USENIX Security Symposium
• Differential Privacy for Text Analytics via Natural Text Sanitization
  Texts convey sophisticated knowledge. However, texts also convey sensitive information. Despite the success of general-purpose language models and domain-specific mechanisms with differential privacy (DP), existing text sanitization mechanisms still provide lo…
  semanticscholar Xiang Yue, Minxin Du, Tianhao Wang, Yaliang Li 等 2021-06-02 置信度 0.74 Findings
• Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
  Differential privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees. This survey provides an overview of the state of the art of differentially private c…
  semanticscholar Lea Demelius, Roman Kern, Andreas Trügler 2023-09-28 置信度 0.74 ACM Computing Surveys
• A Survey on Differential Privacy for Medical Data Analysis
  Machine learning methods promote the sustainable development of wise information technology of medicine (WITMED), and a variety of medical data brings high value and convenience to medical analysis. However, the applications of medical data have also been conf…
  europepmc Wei-kang Liu, Yanchun Zhang, Han Yang, Qinxue Meng 2023 置信度 0.80 Annals of Data Science
• Optimal Accounting of Differential Privacy via Characteristic Function
  Characterizing the privacy degradation over compositions, i.e., privacy accounting, is a fundamental topic in differential privacy (DP) with many applications to differentially private machine learning and federated learning. We propose a unification of recent…
  semanticscholar Yuqing Zhu, Jinshuo Dong, Yu-Xiang Wang 2021-06-16 置信度 0.74 International Conference on Artificial Intelligence and Statistics
• Bounded and Unbiased Composite Differential Privacy
  The objective of differential privacy (DP) is to protect privacy by producing an output distribution that is indistinguishable between any two neighboring databases. However, traditional differentially private mechanisms tend to produce unbounded outputs in or…
  semanticscholar Kai Zhang, Yanjun Zhang, Ruoxi Sun, Pei-Wei Tsai 等 2023-11-04 置信度 0.74 IEEE Symposium on Security and Privacy
• Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
  In this article, we present a detailed review of current practices and state-of-the-art methodologies in the field of differential privacy (DP), with a focus of advancing DP's deployment in real-world applications. Key points and high-level contents of the art…
  semanticscholar Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu 等 2023-04-14 置信度 0.74