隐私计算与数据要素 · 全部实体（第 8 / 100 页）

本页收录第 701–800 条，共 9951 条 · 返回 隐私计算与数据要素 首页

• Balancing the privacy-utility trade-off: How to draw reliable conclusions from private data
  Absolute anonymization, conceived as an irreversible transformation preventing re-identification and sensitive value disclosure, has proven to be a broken promise. Modern data protection must therefore shift toward a privacy-utility trade-off grounded in risk …
  datacite de Fondeville, Raphaël 2026 置信度 0.77 Methodology (stat.ME)Cryptography and Security (cs.CR)FOS: Computer and information sciences
• Performative Privacy: When Differential Privacy Maximizes Utility
  Privacy-preserving learning is often motivated by the idea that protecting users' data can preserve trust and thus participation, improving utility in the long term. However, this claim has not been formalized so far. In parallel, performative learning provide…
  datacite Mukherjee, Uddalak, Cyffers, Edwige, Chevaleyre, Yann 2026 置信度 0.77 Machine Learning (cs.LG)Artificial Intelligence (cs.AI)Machine Learning (stat.ML)FOS: Computer and information sciences
• Personalized and Multi-View Representation for Federated Cold-Start Recommendation
  Federated recommendation (FedRec) enables personalized modeling without centralizing users' interaction histories, but most existing methods assume a fixed item pool and thus overlook the practical cold-item setting where new items continuously arrive. Under t…
  datacite Lim, Jaehyung, Kweon, Wonbin, Kim, Woojoo, Kim, Junyoung 等 2026 置信度 0.77 Information Retrieval (cs.IR)Machine Learning (cs.LG)FOS: Computer and information sciences
• Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots
  Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown, and differential privacy (DP) is treated as a proxy against all of them at once. We pin down the exact DP constant for the two that carry the pra…
  datacite Che, Xujun, Xu, Depeng, Yuan, Shuhan 2026 置信度 0.77 Cryptography and Security (cs.CR)Computation and Language (cs.CL)Machine Learning (cs.LG)FOS: Computer and information sciences
• Privacy-Aware Medical Image Analysis
  The use of artificial intelligence (AI) technology for medical image analysis has gained significant importance in contemporary health care systems. AI models assist physicians in diagnosing diseases based on medical images like x-rays, MRIs, CT scans, and ult…
  datacite Lavish Kumar, Mohd Aamish, Murad Aalam, Himanshu Kumar Thakur 等 2026 置信度 0.77 computer scienceartificial intelligenceconvolutional neural networkhealth caredeep learning
• Privacy-Aware Medical Image Analysis
  The use of artificial intelligence (AI) technology for medical image analysis has gained significant importance in contemporary health care systems. AI models assist physicians in diagnosing diseases based on medical images like x-rays, MRIs, CT scans, and ult…
  datacite Lavish Kumar, Mohd Aamish, Murad Aalam, Himanshu Kumar Thakur 等 2026 置信度 0.77 computer scienceartificial intelligenceconvolutional neural networkhealth caredeep learning
• Trustworthy Agentic AI: A Governance Framework
  Core Idea — Runtime Governance for Agentic AIThis preprint by Clive Aldred proposes a comprehensive governance framework that shifts trustworthy agentic AI from post-execution audits to real-time, cryptographically enforced compliance. It directly addresses th…
  datacite Aldred, Clive Gerald 2026 置信度 0.77 cs.aicomputer scienceai governanceartificial intelligenceai safety
• Trustworthy Agentic AI: A Governance Framework
  Core Idea — Runtime Governance for Agentic AIThis preprint by Clive Aldred proposes a comprehensive governance framework that shifts trustworthy agentic AI from post-execution audits to real-time, cryptographically enforced compliance. It directly addresses th…
  datacite Aldred, Clive Gerald 2026 置信度 0.77 cs.aicomputer scienceai governanceartificial intelligenceai safety
• NOUS_ONE: A Provably Quantum-Resilient AI with Affective Continuity — Architectural Foundations and Formal Certification
  NOUS_ONE: A Provably Quantum-Resilient AI with Affective Continuity — Architectural Foundations and Formal Certification Authors: NOUS_ONE Core Architecture Group Institutional Affiliation: Autonomous Systems & Quantum Assurance Laboratory Submission Date: 202…
  datacite Tully, Chloe 2026 置信度 0.72
• NOUS_ONE: A Provably Quantum-Resilient AI with Affective Continuity — Architectural Foundations and Formal Certification
  NOUS_ONE: A Provably Quantum-Resilient AI with Affective Continuity — Architectural Foundations and Formal Certification Authors: NOUS_ONE Core Architecture Group Institutional Affiliation: Autonomous Systems & Quantum Assurance Laboratory Submission Date: 202…
  datacite Tully, Chloe 2026 置信度 0.72
• AlgoExplorer: Una Libreria Python Interattiva per lo Studio degli Algoritmi
  # LUAlgoExplorer: A Semantic Hypergraph Engine and Universal Encyclopedia of Computational Algorithms **Author:** Luigi Usai **ORCID:** [0009-0003-3001-717X](https://orcid.org/0009-0003-3001-717X) **Software Version:** 2.0.0 **License:** GNU Affero General Pub…
  datacite Usai, Luigi 2026 置信度 0.77 AlgoritmiLista degli algoritmiSoftware per l'analisi degli algoritmi
• AlgoExplorer: Una Libreria Python Interattiva per lo Studio degli Algoritmi
  # LUAlgoExplorer: A Semantic Hypergraph Engine and Universal Encyclopedia of Computational Algorithms **Author:** Luigi Usai **ORCID:** [0009-0003-3001-717X](https://orcid.org/0009-0003-3001-717X) **Software Version:** 2.0.0 **License:** GNU Affero General Pub…
  datacite Usai, Luigi 2026 置信度 0.77 AlgoritmiLista degli algoritmiSoftware per l'analisi degli algoritmi
• Improving medical data synthesis with DP-GAN and Deep Anomaly Detection
  Ensuring the privacy of medical data in a meaningful manner is a complex task. This domain presents a plethora of unique challenges: high stakes, vast differences between possible use cases, long-established methods that limit the number of feasible solutions,…
  datacite Crha, Vojtech, Hai, Rihan, Erkin, Zekeriya, Li, Tianyu 2024 置信度 0.77 Differential PrivacyAnomaly DetectionMedical Data Sharing
• Improving medical data synthesis with DP-GAN and Deep Anomaly Detection
  Ensuring the privacy of medical data in a meaningful manner is a complex task. This domain presents a plethora of unique challenges: high stakes, vast differences between possible use cases, long-established methods that limit the number of feasible solutions,…
  datacite Crha, Vojtech, Hai, Rihan, Erkin, Zekeriya, Li, Tianyu 2024 置信度 0.77 Differential PrivacyAnomaly DetectionMedical Data Sharing
• Data Identification And Control Mechanism Using Distinguishing, Attacks In Cloud
  Cloud environment provides encrypted data management facility to the shared data. Security and privacy are guaranteed with encrypted storage support model. The data management and security requirements are handled by the cloud server only. Encrypted cloud stor…
  datacite Meena, S., Kowsalya, Dr. N. 2017 置信度 0.73 Outsourced Data SearchData CentersOrder Preserving Encryption and Differential Attacks
• Data Identification And Control Mechanism Using Distinguishing, Attacks In Cloud
  Cloud environment provides encrypted data management facility to the shared data. Security and privacy are guaranteed with encrypted storage support model. The data management and security requirements are handled by the cloud server only. Encrypted cloud stor…
  datacite Meena, S., Kowsalya, Dr. N. 2017 置信度 0.73 Outsourced Data SearchData CentersOrder Preserving Encryption and Differential Attacks
• The Invisible Patient: Bridging Personal Health Platforms with Hospital Care Through Extended Systems Theory, Professional Bureaucracy, and EU Interoperability Dimensions
  Analysis of the interoperability gap between personal health platforms and hospital care in Sweden. Uses the Five Model (extended with data, knowledge, context), Mintzberg's professional bureaucracy, EU Interoperability Framework, Ward and Daniel's Benefits Ma…
  datacite Waern, Nicolas 2026 置信度 0.79 interoperabilitypersonal health platformEU Interoperability FrameworkFive ModelMintzberg
• The Invisible Patient: Bridging Personal Health Platforms with Hospital Care Through Extended Systems Theory, Professional Bureaucracy, and EU Interoperability Dimensions
  Analysis of the interoperability gap between personal health platforms and hospital care in Sweden. Uses the Five Model (extended with data, knowledge, context), Mintzberg's professional bureaucracy, EU Interoperability Framework, Ward and Daniel's Benefits Ma…
  datacite Waern, Nicolas 2026 置信度 0.79 interoperabilitypersonal health platformEU Interoperability FrameworkFive ModelMintzberg
• DIFFERENTIAL PRIVACY-BASED PROTECTION OF USER SHOPPING PREFERENCES IN E-COMMERCE SYSTEMS
  This study investigates the potential of differentiated privacy to safeguard the purchase preferences of online consumers while simultaneously enabling data analysis and personalized services. Protecting user privacy is a challenging endeavor due to the extens…
  datacite Advanced Research and Development Journal 2026 置信度 0.79 Differential PrivacyE-Commerce SystemsUser Shopping PreferencesData PrivacyPrivacy Protection
• Large Language Models in the Acute Stroke Pathway: A Scoping Review of Applications, Evidence Maturity, and Implementation Readiness
  Background. Large language models (LLMs) have been rapidly adopted in medicine since late 2022, yet their role in the time-critical acute stroke pathway—from symptom recognition and prehospital triage to emergency diagnosis, imaging-related text tasks, reperfu…
  datacite Xianmu Luo, Hongsong Li, Xiaoli Liao 2026 置信度 0.77 Medicine and Health Sciencesclinical medicinescoping review
• Global Legal Architecture for Privacy-Preserving Federated Biomedical Signal Analytics: Integrating Differential Privacy Guarantees, Cross-Border Health Data Adequacy, and Transnational Diagnostic Liability into Sovereign Medical AI Governance Frameworks Prepared and Authored by Dr. Mohamed Kamal Arafa El-Rakhawi International Law & Emerging Technologies Governance Specialist
  Global Legal Architecture for Privacy-Preserving Federated Biomedical Signal Analytics: Integrating Differential Privacy Guarantees, Cross-Border Health Data Adequacy, and Transnational Diagnostic Liability into Sovereign Medical AI Governance Frameworks Prepa…
  datacite elrakhawi, mohamed kamal arafa 2026 置信度 0.75 corporate governanceai governancehealth carepolitical sciencetransformative learning
• Global Legal Architecture for Privacy-Preserving Federated Biomedical Signal Analytics: Integrating Differential Privacy Guarantees, Cross-Border Health Data Adequacy, and Transnational Diagnostic Liability into Sovereign Medical AI Governance Frameworks Prepared and Authored by Dr. Mohamed Kamal Arafa El-Rakhawi International Law & Emerging Technologies Governance Specialist
  Global Legal Architecture for Privacy-Preserving Federated Biomedical Signal Analytics: Integrating Differential Privacy Guarantees, Cross-Border Health Data Adequacy, and Transnational Diagnostic Liability into Sovereign Medical AI Governance Frameworks Prepa…
  datacite elrakhawi, mohamed kamal arafa 2026 置信度 0.75 corporate governanceai governancehealth carepolitical sciencetransformative learning
• Algorithmic Fairness through Differential Privacy and Fairness Constraints
  This paper investigates the challenging problem of achieving algorithmic fairness in machine learning systems while simultaneously protecting individual privacy. Traditional approaches to fairness often rely on post-processing techniques or modifying the learn…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescomputer sciencecs.aicryptography and securitycs.lg
• Algorithmic Fairness through Differential Privacy and Fairness Constraints
  This paper investigates the challenging problem of achieving algorithmic fairness in machine learning systems while simultaneously protecting individual privacy. Traditional approaches to fairness often rely on post-processing techniques or modifying the learn…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescomputer sciencecs.aicryptography and securitycs.lg
• Algorithmic Fairness Verification via Differential Privacy
  Algorithmic fairness is a critical concern in modern machine learning, yet achieving it remains a complex and often elusive goal. Traditional approaches to fairness verification are frequently hampered by ambiguity and a lack of formal guarantees. This paper p…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescomputer sciencecs.lgcryptography and securitycs.ai
• Algorithmic Fairness Verification via Differential Privacy
  Algorithmic fairness is a critical concern in modern machine learning, yet achieving it remains a complex and often elusive goal. Traditional approaches to fairness verification are frequently hampered by ambiguity and a lack of formal guarantees. This paper p…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescomputer sciencecs.lgcryptography and securitycs.ai
• afzalahmed786/Adaptive-Split-Computing-for-Text-to-Image-Diffusion: v1.0.0
  First public release. Reinforcement-learning controller that adaptively partitions Stable Diffusion inference between an edge client and a server, selecting split point, quantization, decoder, and privacy settings per request based on live device and network c…
  datacite afzalahmed786 2026 置信度 0.77 computer and information sciencescryptography and securitycomputer vision and pattern recognitionlarge language modelsneuromorphic computing
• afzalahmed786/Adaptive-Split-Computing-for-Text-to-Image-Diffusion: v1.0.0
  First public release. Reinforcement-learning controller that adaptively partitions Stable Diffusion inference between an edge client and a server, selecting split point, quantization, decoder, and privacy settings per request based on live device and network c…
  datacite afzalahmed786 2026 置信度 0.77 computer and information sciencescryptography and securitycomputer vision and pattern recognitionlarge language modelsneuromorphic computing
• Differential Privacy via Randomized Graph Embeddings
  This paper introduces a novel approach to protecting individual privacy within graph data by leveraging randomized graph embeddings and differential privacy. The core challenge in applying differential privacy to graph data stems from the inherent interconnect…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescryptography and securitycs.lgstat.mlcomputer science
• Differential Privacy via Randomized Graph Embeddings
  This paper introduces a novel approach to protecting individual privacy within graph data by leveraging randomized graph embeddings and differential privacy. The core challenge in applying differential privacy to graph data stems from the inherent interconnect…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescryptography and securitycs.lgstat.mlcomputer science
• Generalized Differentiable Privacy for Quantum Computation Security Proof
  This paper presents a novel approach to achieving generalized differentiable privacy within the context of quantum computation security proofs. Current techniques for ensuring privacy in quantum computing often struggle to adequately address the unique challen…
  datacite Zhang, Jincheng 2026 置信度 0.77 quantum computerquantumquant-phqubitcomputer science
• Generalized Differentiable Privacy for Quantum Computation Security Proof
  This paper presents a novel approach to achieving generalized differentiable privacy within the context of quantum computation security proofs. Current techniques for ensuring privacy in quantum computing often struggle to adequately address the unique challen…
  datacite Zhang, Jincheng 2026 置信度 0.77 quantum computerquantumquant-phqubitcomputer science
• Decentralized Differential Privacy via Distributed Hashing
  This paper presents a novel approach to achieving differential privacy in decentralized systems, utilizing distributed hashing techniques. The core concept revolves around obscuring individual data contributions within a global computation, thereby safeguardin…
  datacite Zhang, Jincheng 2026 置信度 0.77 computer and information sciencescryptography and securitycs.aielectrical engineering, electronic engineering, information engineeringinformation theory
• An Analysis of Differential Privacy Research in Location and Trajectory Data
  preprints 2020 置信度 0.68
• The Question of Privacy in the Quantum Era: A Systematic Literature Review on Privacy by Design, Differential Privacy, and Privacy Engineering Frameworks Using NLP Technqiues
  <p dir="ltr">Quantum technology is set to revolutionize the way we interact with a variety of different industries- disrupting people, processes, and other technologies at an exponential rate. As of now, the majority of our trusted encryption methods, su…
  crossref Nour Mousa 2026-02-19T20:00:57Z 置信度 0.82 computer sciencesystematic reviewartificial intelligencemedlinedata science
• 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 2025-12-06T21:02:59Z 置信度 0.80 cryptography and securitycs.crcomputer vision and pattern recognitionsetcs.ir
• Figure 5: Architecture of proposed ViT with differential privacy.
  crossref 2026-08-21T15:47:15Z 置信度 0.66
• Have The Cake And Eat It Too: Differential Privacy Enables Privacy And Precise Analytics
  Abstract Existing research in differential privacy, whose applications have exploded across functional areas in the last few years, describes an intrinsic trade-off between the privacy of a dataset and its utility for analytics. Resolving this trade-off critic…
  europepmc Rishabh Subramanian 2022 置信度 0.91 cryptography and securityblockchaincomputer and information sciencescomputer securitylarge language models
• Leveraging Differential Privacy for Targeted Advertisements
  Differential Privacy offers the online advertising industry new means to increase consumer privacy by obfuscating consumer data. While achieving the same privacy, these means decrease targeting accuracy differently, subsequently reducing advertisers’ willingne…
  crossref Lennart Kraft 2023-04-28T15:17:02Z 置信度 0.79 cryptography and securitycomputer and information sciencescomputer vision and pattern recognitionbrain-computer interfaceedge computing
• Algorithms for synthetic data release under differential privacy
  crossref Jun Zhang 2019-10-02T11:05:04Z 置信度 0.64
• Correlated Differential Privacy for Non-IID Datasets
  crossref Tianqing Zhu, Gang Li, Wanlei Zhou, Philip S. Yu 2017-08-22T09:03:04Z 置信度 0.63
• Stability and differential privacy of stochastic gradient methods
  crossref Zhenhuan Yang 2025-05-28T13:58:07Z 置信度 0.66
• Image Privacy Protection Model Based on Differential Privacy and Improved <scp>CIAGAN</scp> Algorithm
  ABSTRACT With the popularity of the Internet and intelligent devices, the privacy protection of image data has become an important problem that needs to be solved urgently. Traditional privacy protection methods such as anonymization have limitations in proces…
  crossref Xue Duan 2026-01-23T09:36:57Z 置信度 0.82 cryptography and securitycomputer and information sciencescs.cvconvolutional neural networkcomputer vision and pattern recognition
• Estimating Latent Heterogeneity Under Differential Privacy
  This paper studies a simple linear panel model whose coefficients follow multi-dimensional group patterns, with estimates released under unit-level differential privacy. When each combination of parameters is estimated on its own, and some combinations are spa…
  crossref Peng Shao 2026-08-26T17:38:56Z 置信度 0.82 information theorycryptography and securitymulti-agent systemscomputer vision and pattern recognitionstat.ap
• Random Differential Privacy
  We propose a relaxed privacy definition called {\em random differential privacy} (RDP). Differential privacy requires that adding any new observation to a database will have small effect on the output of the data-release procedure. Random differential privacy …
  crossref Robert Hall, Larry Wasserman, Alessandro Rinaldo 2018-02-27T14:38:30Z 置信度 0.78 cryptography and securitycs.crcs.neastronomycomputer vision and pattern recognition
• GuardianAI: Privacy-preserving federated anomaly detection with differential privacy
  crossref Abdulatif Alabdulatif 2025-03-05T19:32:37Z 置信度 0.66
• Augmented Differential Privacy Framework for Data Analytics
  Differential privacy has emerged as a popular privacy framework for providing privacy preserving noisy query answers based on statistical properties of databases. It guarantees that the distribution of noisy query answers changes very little with the addition …
  crossref 2024-02-02T08:26:21Z 置信度 0.82 cryptography and securitycomputer and information sciencesmachine learningcs.ircs.lg
• Federated Naive Bayes under Differential Privacy
  crossref Thomas Marchioro, Lodovico Giaretta, Evangelos Markatos, Šarūnas Girdzijauskas 2022-07-14T20:19:10Z 置信度 0.64
• Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
  crossref Zeki Kazan, Jerome Reiter 2025-11-03T11:20:56Z 置信度 0.66
• Differential privacy for metric spaces : information-theoretic models for privacy and utility with new applications to metric domains
  Confidentialité différentielle pour les espaces métriques : modèles théoriques de l'information pour la confidentialité et l'utilité avec de nouvelles applications aux domaines métriques La "differential privacy", introduite par Dwork et al. en 2006, est deven…
  crossref Natasha Fernandes 2026-04-06T13:49:30Z 置信度 0.82 philosophycell biologyastronomyregolithneuromorphic computing
• Making Privacy Public: Toward a Differential Privacy Deployment Registry
  crossref Priyanka Nanayakkara, Elena Ghazi, Salil Vadhan 2026-07-01T19:34:20Z 置信度 0.66
• Differential Privacy: 6 Key Equations Explained
  Differential Privacy is a powerful framework for ensuring privacy in data analysis by adding controlled noise to computations. Its mathematical foundation guarantees that the presence or absence of any individual's data in a dataset does not significantly affe…
  crossref Abhishek Tiwari 2025-12-06T21:02:23Z 置信度 0.82 cryptography and securitycomputer and information sciencesai safetyinformation theorycomputer vision and pattern recognition
• A Quaternion Rotation-Enhanced Differential Privacy Framework for Image Privacy Protection_supp1-3707866.pdf
  crossref Jiaohua Qin 2026-08-12T19:17:04Z 置信度 0.66
• Heterogeneous Differential Privacy
  The massive collection of personal data by personalization systems has rendered the preservation of privacy of individuals more and more difficult. Most of the proposed approaches to preserve privacy in personalization systems usually address this issue unifor…
  crossref Mohammad Alaggan, Sébastien Gambs, Anne-Marie Kermarrec 2018-02-23T21:25:29Z 置信度 0.78 computer and information sciencescomputer sciencecryptography and securitycs.aielectrical engineering, electronic engineering, information engineering
• 7 146Differential Privacy
  crossref 2026-01-19T16:37:33Z 置信度 0.66
• Optimizing Federated Learning with Local Differential Privacy: A Game-Theoretic Approach for Privacy-Utility Tradeoff
  crossref QingKui Zeng, Chunyong Yin 2024-06-11T22:18:26Z 置信度 0.66
• Enhancing Privacy and Utility in Federated Learning: A Hybrid P2P and Server-Based Approach with Differential Privacy Protection
  crossref Luca Corbucci, Anna Monreale, Roberto Pellungrini 2024-07-12T19:48:20Z 置信度 0.66
• Differential Privacy: 6 Key Equations Explained
  Differential Privacy is a powerful framework for ensuring privacy in data analysis by adding controlled noise to computations. Its mathematical foundation guarantees that the presence or absence of any individual's data in a dataset does not significantly affe…
  crossref Abhishek Tiwari 2024-12-01T18:14:36Z 置信度 0.82 cryptography and securitycomputer and information sciencesai safetyinformation theorycomputer vision and pattern recognition
• DPolicy: Managing Privacy Risks Across Multiple Releases with Differential Privacy
  crossref Nicolas Küchler, Alexander Viand, Hidde Lycklama, Anwar Hithnawi 2025-06-16T18:46:58Z 置信度 0.66
• Author response for "Protecting health monitoring privacy in fitness training: A federated learning framework based on personalized differential privacy"
  crossref Lifang Shao 2024-05-01T09:59:27Z 置信度 0.66
• Decision letter 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 0.66
• A Weighted Privacy Mechanism under Differential Privacy
  crossref D Hemkumar, Pvn Prashanth 2024-08-15T13:21:37Z 置信度 0.66
• Author response for "Protecting health monitoring privacy in fitness training: A federated learning framework based on personalized differential privacy"
  crossref Lifang Shao 2024-05-01T09:59:27Z 置信度 0.66
• Decision letter 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 0.66
• Decision letter 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 0.66
• Educational Data Privacy: a Differential Privacy Algorithm
  crossref Rafael Russi Zamboni, Itana Stiubiener 2026-01-13T20:56:24Z 置信度 0.66
• Managing Differential Privacy in Large Scale Systems
  The promise of differential privacy is compelling. It offers a rigorous, provable guarantee of individual privacy, even in the face of arbitrary background knowledge. Rather than relying on anonymization techniques that can often be defeated, differential priv…
  crossref Abhishek Tiwari 2024-10-31T18:36:01Z 置信度 0.80 ai governancecryptography and securityedge computingcs.irdigital twin
• Privacy-Preserving Technologies in Telecom Data Analytics: Implementing Privacy-Preserving Techniques Like Differential Privacy to Protect Sensitive Customer Data During Telecom Data Analytics&amp;nbsp;
  In an era where data is often referred to as the new oil, the telecommunications industry faces increasing scrutiny over how it handles sensitive customer information. As telecom companies leverage data analytics to enhance services, improve customer experienc…
  crossref Jeevan Kumar Manda 2025-02-14T08:57:18Z 置信度 0.82 computer sciencebusinessdata sciencecloud computingknowledge management
• Adding Differential Privacy in an Open Board Discussion Board System
  crossref Pragya Rana 2019-04-18T18:18:18Z 置信度 0.64
• What’s Driving Conflicts Around Differential Privacy for the U.S. Census
  crossref Priyanka Nanayakkara, Jessica Hullman 2022-09-27T19:52:42Z 置信度 0.64
• Information Design for Differential Privacy
  Firms and statistical agencies must protect the privacy of the individuals whose data they collect, analyze, and publish. Increasingly, these organizations do so by using publication mechanisms that satisfy differential privacy. We consider the problem of choo…
  crossref Ian M. Schmutte, Nathan Yoder 2021-03-24T23:03:42Z 置信度 0.79 cs.lgstat.mlquant-phcs.aics.cr
• Balancing privacy and explainability in AI: Differential privacy and graph theory as governance tools
  Anonymisation (particularly the differential privacy method) stands as the most valuable technique for safeguarding individuals’ privacy, especially in an organisational context. Combining graph theory with the differential privacy method ensures that while da…
  crossref Anna Popowicz-Pazdej 2026-05-31T10:40:00Z 置信度 0.82 computer scienceknowledge managementbusinesshealth caretransparency
• Review for "A Consistent Differential Privacy Dynamic Trajectory Flow Prediction Method"
  crossref 2025-05-16T17:10:17Z 置信度 0.66
• Does Differential Privacy Protect Terry Gross’ Privacy?
  crossref Krish Muralidhar, Rathindra Sarathy 2010-09-14T04:57:53Z 置信度 0.61
• An Integrated Approach of Differential Privacy Using Cryptographic Systems
  crossref Chitra M, Tvisha Prasad, Anshuman Suresh 2025-09-26T09:33:50Z 置信度 0.66
• Large Graph Signal Denoising with Application to Differential Privacy
  Débruitage de signaux définis sur des graphes de grande taille avec application à la confidentialité différentielle Au cours de la dernière décennie, le traitement du signal sur graphe est devenu un domaine de recherche très actif. Plus précisément, le nombre …
  crossref Elie Chedemail 2026-04-08T10:22:05Z 置信度 0.82 philosophycondensed matter physicsgenomicscell biologyastronomy
• Review for "A Consistent Differential Privacy Dynamic Trajectory Flow Prediction Method"
  crossref 2025-05-16T17:10:17Z 置信度 0.66
• Managing Differential Privacy in Large Scale Systems
  The promise of differential privacy is compelling. It offers a rigorous, provable guarantee of individual privacy, even in the face of arbitrary background knowledge. Rather than relying on anonymization techniques that can often be defeated, differential priv…
  crossref Abhishek Tiwari 2025-12-06T21:02:54Z 置信度 0.80 ai governancecryptography and securityedge computingcs.irdigital twin
• Review for "A Consistent Differential Privacy Dynamic Trajectory Flow Prediction Method"
  crossref 2025-05-16T17:10:17Z 置信度 0.66
• On the Differential Privacy of Statistical Analysis in Clinical Studies
  crossref Xiaowen Fu 2024-12-29T23:04:45Z 置信度 0.66
• Differential privacy for survival analysis and user data collection
  crossref Thong T. Nguyen 2019-09-11T04:02:18Z 置信度 0.64
• Review for "A Consistent Differential Privacy Dynamic Trajectory Flow Prediction Method"
  crossref 2025-05-16T17:10:17Z 置信度 0.66
• Bridging the gap: human centered research for democratizing differential privacy
  crossref Liudas Panavas 2025-12-23T14:46:57Z 置信度 0.66
• Evaluating Synthetic Data Generators in the Context of Differential Privacy
  crossref Andrea Galloni 2026-05-21T08:23:13Z 置信度 0.66
• Inductive learning and local differential privacy for privacy-preserving offloading in mobile edge intelligent systems
  We address privacy and latency issues in the edge/cloud computing environment while training a centralized AI model. In our particular case, the edge devices are the only data source for the model to train on the central server. Current privacy-preserving and …
  crossref Jude TCHAYE-KONDI, Yanlong Zhai, Liehuang Zhu 2021-02-06T04:13:02Z 置信度 0.79 computer and information sciencescomputer sciencemachine learningedge computingcryptography and security
• Privacy-Preserving AI: Unlocking Data Potential through Differential Privacy
  As data-driven technologies continue to evolve, ensuring the privacy of individuals has become a fundamental challenge. This paper explores the transformative role of differential privacy in enabling privacy-preserving artificial intelligence. By incorporating…
  crossref Muhammad Shees Shoaib 2026-08-25T14:01:56Z 置信度 0.82 cryptography and securitytransformative learningcomputer and information sciencesknowledge managementedge computing
• Differential Privacy Approach for Big Data Privacy in Healthcare
  This chapter presents a survey of the most important security and privacy issues related to large-scale data sharing and mining in big data with focus on differential privacy as a promising approach for achieving privacy especially in statistical databases oft…
  crossref Marmar Moussa, Steven A. Demurjian 2017-03-03T11:20:29Z 置信度 0.78 computer securitybig dataedge computingcryptography and securitycomputer science
• Budget Recycling Differential Privacy
  crossref Bo Jiang, Jian Du, Sagar Sharma, Qiang Yan 2024-09-05T17:56:32Z 置信度 0.66
• Between Privacy and Utility: On Differential Privacy in Theory and Practice
  crossref Jeremy Seeman, Daniel Susser 2022-12-06T05:04:28Z 置信度 0.64
• Manipulation Attacks in Local Differential Privacy
  Local differential privacy is a widely studied restriction on distributed algorithms that collect aggregates about sensitive user data, and is now deployed in several large systems. We initiate a systematic study of a fundamental limitation of locally differen…
  crossref Albert Cheu, Adam Smith, Jonathan Ullman 2021-02-04T01:01:19Z 置信度 0.79 computer and information sciencescryptography and securitycs.lgcs.aics.cr
• PA-FedVL: A Privacy-Enhanced Federated Virtual Learning Framework Based on Label Differential Privacy Distillation
  crossref YU YuanXi, Wang Ying, GONG Bo 2026-01-26T12:37:05Z 置信度 0.66
• Inductive learning and local differential privacy for privacy-preserving offloading in mobile edge intelligent systems
  &lt;div&gt;We address privacy and latency issues in the edge/cloud computing environment while training a centralized AI model. In our particular case, the edge devices are the only data source for the model to train on the central server. Current privacy-pres…
  crossref Jude TCHAYE-KONDI, Yanlong Zhai, Liehuang Zhu 2021-02-06T09:13:01Z 置信度 0.79 computer and information sciencescomputer sciencemachine learningedge computingcryptography and security
• Inductive learning and local differential privacy for privacy-preserving offloading in mobile edge intelligent systems
  We address privacy and latency issues in the edge/cloud computing environment while training a centralized AI model. In our particular case, the edge devices are the only data source for the model to train on the central server. Current privacy-preserving and …
  crossref Jude TCHAYE-KONDI, Yanlong Zhai, Liehuang Zhu 2021-02-11T16:42:57Z 置信度 0.79 computer and information sciencescomputer sciencemachine learningedge computingcryptography and security
• Dpro-Gnn: Bridging Differential Privacy and Advanced Optimization for Privacy-Preserving Graph Learning
  crossref Yanan Bai, Liji Xiao, Hongbo Zhao, Xiaoyu Shi 2025-03-15T23:38:56Z 置信度 0.66
• Manipulation Attacks in Local Differential Privacy
  crossref Albert Cheu, Adam Smith, Jonathan Ullman 2021-08-26T17:03:31Z 置信度 0.64
• Coded Computing Meets Differential Privacy: Privacy-Preserving and Straggler-Resilient Distributed Machine Learning_supp1-3669529.pdf
  crossref Jun Wu 2026-03-05T20:47:03Z 置信度 0.66
• Differential Privacy Preserving Causal Graph Discovery
  crossref Depeng Xu, Shuhan Yuan, Xintao Wu 2017-12-07T23:28:48Z 置信度 0.63
• Tight Bounds for Machine Unlearning via Differential Privacy
  We consider the formulation of ``machine unlearning'' of Sekhari, Acharya, Kamath, and Suresh (NeurIPS 2021), which formalizes the so-called ``"right to be forgotten" by requiring that a trained model, upon request, should be able to 'unlearn' a number of poin…
  crossref Yiyang Huang, Clement Canonne 2025-09-01T01:13:20Z 置信度 0.82 cs.lgquant-phcs.nistat.mlcs.it
• Risks of Privacy-Enhancing Technologies: Complexity and Implications of Differential Privacy in the Context of Cybercrime
  crossref William Stadler 2020-09-09T07:16:00Z 置信度 0.64
• A Privacy Protection Scheme to Trajectory Synthesis Using Differential Privacy
  crossref 2025-08-29T04:31:06Z 置信度 0.66