BestHub
Sign in
Tagged articles
12 articles
Page 1 of 1
Alimama Tech
Alimama Tech
Sep 3, 2025 · Artificial Intelligence

Privacy-Preserving Machine Learning: Balancing Data Utility and Confidentiality

Privacy-Preserving Machine Learning (PPML) integrates cryptographic techniques such as federated learning, differential privacy, homomorphic encryption, and secure multi-party computation to enable model training and inference on encrypted or distributed data, thereby breaking data silos while safeguarding privacy across sectors like healthcare, finance, and advertising.

Federated LearningHomomorphic Encryptionmachine learning
0 likes · 18 min read
Privacy-Preserving Machine Learning: Balancing Data Utility and Confidentiality
AntTech
AntTech
Dec 6, 2024 · Artificial Intelligence

Nimbus: Secure and Efficient Two‑Party Inference for Transformers

The paper introduces Nimbus, a two‑party privacy‑preserving inference framework for Transformer models that leverages a client‑side outer‑product linear‑layer protocol and distribution‑aware polynomial approximations for non‑linear layers, achieving up to five‑fold speedups with negligible accuracy loss.

Homomorphic EncryptionPerformance OptimizationTransformer
0 likes · 15 min read
Nimbus: Secure and Efficient Two‑Party Inference for Transformers
AntTech
AntTech
Nov 12, 2024 · Artificial Intelligence

Rhombus: Fast Homomorphic Matrix‑Vector Multiplication for Secure Two‑Party Inference – Paper Overview and Live Presentation

The article introduces the Rhombus protocol, a fast homomorphic matrix‑vector multiplication scheme that reduces ciphertext rotations and achieves O(1) communication complexity, enabling efficient privacy‑preserving two‑party inference, and announces a live streaming session where the first author will discuss its technical details and experimental results.

Homomorphic EncryptionPrivacy-Preserving Machine LearningRhombus protocol
0 likes · 3 min read
Rhombus: Fast Homomorphic Matrix‑Vector Multiplication for Secure Two‑Party Inference – Paper Overview and Live Presentation
vivo Internet Technology
vivo Internet Technology
Aug 23, 2023 · Artificial Intelligence

Federated Learning: Privacy-Preserving Collaborative AI Across Data Islands

Federated learning enables multiple organizations to jointly train high‑performing AI models without sharing raw data, using techniques such as secure multi‑party computation, differential privacy, and homomorphic encryption, thereby overcoming data‑island and regulatory constraints and supporting applications in mobile edge AI, finance, retail, and healthcare.

Data IslandFederated LearningHomomorphic Encryption
0 likes · 19 min read
Federated Learning: Privacy-Preserving Collaborative AI Across Data Islands
Tencent Tech
Tencent Tech
Dec 9, 2022 · Artificial Intelligence

How Tencent’s Angel PowerFL Team Dominated iDASH with Homomorphic Encryption

Tencent’s Angel PowerFL team clinched the iDASH homomorphic encryption champion and secured top spots in MPC and SGX tracks, showcasing innovative privacy‑preserving machine‑learning models, CKKS‑based encrypted inference, and a scalable SGX clustering solution that push the boundaries of secure computation.

Homomorphic EncryptionPrivacy ComputingiDASH
0 likes · 5 min read
How Tencent’s Angel PowerFL Team Dominated iDASH with Homomorphic Encryption
AntTech
AntTech
Jun 16, 2022 · Information Security

Privacy Computing: How Digital Technologies Address Privacy Protection Pain Points

This article examines the rapid growth of privacy computing in China, outlining policy and market drivers, explaining key technologies such as secure multiparty computation, trusted execution environments, homomorphic encryption, differential privacy and federated learning, and discussing the legal, technical and ecosystem challenges that hinder its wider adoption.

Federated LearningHomomorphic EncryptionPrivacy Computing
0 likes · 11 min read
Privacy Computing: How Digital Technologies Address Privacy Protection Pain Points
DataFunSummit
DataFunSummit
Jun 4, 2022 · Information Security

Privacy-Preserving Computation: Innovations and Practices at Jiànxìn Jīnke

This article outlines the rapid growth of data, the rising privacy risks, and Jiànxìn Jīnke's innovative platform for privacy‑preserving computation that integrates federated learning, secure multi‑party computation, homomorphic encryption, and industry‑level applications such as joint risk control and marketing models.

Homomorphic Encryptionfinancial technologysecure multi-party computation
0 likes · 8 min read
Privacy-Preserving Computation: Innovations and Practices at Jiànxìn Jīnke
JD Tech Talk
JD Tech Talk
Sep 30, 2020 · Artificial Intelligence

Secure Training Methods for Federated Transfer Learning

This article reviews the model structure of federated transfer learning and details three secure training approaches—additive homomorphic encryption, ABY, and SPDZ—combined with polynomial approximation, explaining their protocols, steps, and the role of federated transfer learning within the broader federated learning landscape.

Homomorphic Encryptionprivacysecure computation
0 likes · 11 min read
Secure Training Methods for Federated Transfer Learning
Tencent Cloud Developer
Tencent Cloud Developer
Sep 25, 2020 · Artificial Intelligence

Privacy-Preserving Federated Learning for Financial Risk Control Using Homomorphic Encryption

Tencent Shield‑Federated Computing enables banks to jointly train Gradient Boosted Decision Trees and Logistic Regression with external data owners by using homomorphic encryption to perform encrypted variable and split‑point searches, gradient aggregation, and model updates, delivering near‑centralized accuracy, up to 70 % speed gains, and full data confidentiality for financial risk control.

Federated LearningGradient Boosted TreesHomomorphic Encryption
0 likes · 15 min read
Privacy-Preserving Federated Learning for Financial Risk Control Using Homomorphic Encryption
dbaplus Community
dbaplus Community
Oct 20, 2019 · Blockchain

Can Blockchain Solve Privacy Risks? From GDPR to Zero‑Knowledge Proofs

The talk outlines how recent privacy regulations like GDPR expose data sovereignty, jurisdiction, and fines, then explains how blockchain’s distributed ledger, consensus, smart contracts, and cryptographic techniques—including homomorphic encryption and zero‑knowledge proofs—address trust gaps and privacy challenges, illustrated with real‑world financial use cases and a telecom‑backed BaaS platform.

BaaSFinancial ServicesGDPR
0 likes · 23 min read
Can Blockchain Solve Privacy Risks? From GDPR to Zero‑Knowledge Proofs
UCloud Tech
UCloud Tech
May 25, 2018 · Information Security

How Blockchain and Advanced Cryptography Secure Data Flow: A Deep Dive

An in‑depth overview explains how blockchain, homomorphic encryption, zero‑knowledge proofs, group and ring signatures, and differential privacy collectively secure data flow, enabling trusted sharing while preserving ownership and privacy across providers, consumers, and algorithm services.

BlockchainData FlowHomomorphic Encryption
0 likes · 11 min read
How Blockchain and Advanced Cryptography Secure Data Flow: A Deep Dive