differential privacy

AntTech

Dec 2, 2024 · Artificial Intelligence

Ant Group’s Morse & ARCLab Wins Both Attack and Defense Tracks in NeurIPS 2024 LLM Privacy Challenge

Ant Group’s Morse & ARCLab team secured the champion title in the attack track and the best practical defense award in the LLM Privacy Challenge at NeurIPS 2024, showcasing cutting‑edge methods for extracting training data from large language models and protecting model privacy with data sanitization and differential privacy techniques.

AI securityLLM privacyNeurIPS

0 likes · 5 min read

Ant Group’s Morse & ARCLab Wins Both Attack and Defense Tracks in NeurIPS 2024 LLM Privacy Challenge

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.

Artificial IntelligenceData IslandFederated Learning

0 likes · 19 min read

Federated Learning: Privacy-Preserving Collaborative AI Across Data Islands

AntTech

May 4, 2023 · Artificial Intelligence

Privacy Risks and Differentially Private Defense for Federated Knowledge Graph Representation Learning

This paper investigates the privacy leakage risks of federated knowledge graph representation learning, designs three membership inference attacks to quantify the threats, and proposes DP‑Flames, a differential‑privacy‑based defense that leverages gradient sparsity to achieve a favorable privacy‑utility trade‑off.

DP-FlamesFederated Learningdifferential privacy

0 likes · 15 min read

Privacy Risks and Differentially Private Defense for Federated Knowledge Graph Representation Learning

AntTech

Dec 5, 2022 · Artificial Intelligence

Four AAAI‑23 Papers from Ant Security Lab on Adversarial 3D Point Clouds, GNN‑Based Anti‑Money Laundering, Spiking Neural Network Dynamic Graph Learning, and Differential‑Private Adaptive Clipping

Ant Security Lab reports four AAAI‑23 accepted papers that introduce PF‑Attack for transferable 3D adversarial point clouds, AMAP a GNN‑driven anti‑money‑laundering framework, SpikeNet a spiking‑neural‑network approach for efficient dynamic graph representation, and DP‑PSAC a per‑sample adaptive clipping method for differential privacy, each with experimental validation and expert commentary.

AAAI-23Graph Neural Networksadversarial attacks

0 likes · 18 min read

Four AAAI‑23 Papers from Ant Security Lab on Adversarial 3D Point Clouds, GNN‑Based Anti‑Money Laundering, Spiking Neural Network Dynamic Graph Learning, and Differential‑Private Adaptive Clipping

DataFunSummit

Nov 28, 2022 · Artificial Intelligence

Introduction to Federated Learning: Concepts, Key Technologies, and the Dianshi Federated Learning Platform

This article introduces the concept of federated learning, outlines its industry opportunities and challenges, explains the evolution of data‑sharing technologies, details core techniques such as MPC, TEE, and differential privacy, and presents the architecture and capabilities of the Dianshi federated learning platform.

AIFederated LearningMPC

0 likes · 20 min read

Introduction to Federated Learning: Concepts, Key Technologies, and the Dianshi Federated Learning Platform

DataFunSummit

Oct 2, 2022 · Artificial Intelligence

Differential Privacy: Principles, Algorithms, and Applications in Data Security

This article presents an in‑depth overview of differential privacy, covering its motivation, mathematical definition, noise‑addition mechanisms, a heterogeneous‑data variant, and practical applications such as federated learning, while also discussing challenges, theoretical guarantees, experimental results, and future research directions.

Data SecurityFederated LearningPrivacy-Preserving Algorithms

0 likes · 11 min read

Differential Privacy: Principles, Algorithms, and Applications in Data Security

AntTech

Sep 29, 2022 · Artificial Intelligence

Privacy-Preserving Vertical Federated Graph Neural Network for Node Classification

This article presents VFGNN, a privacy‑preserving vertical federated graph neural network designed for node classification, detailing its architecture, differential‑privacy enhancements, and experimental results that demonstrate superior accuracy over single‑party baselines across multiple graph datasets.

Federated LearningGraph Neural NetworksNode Classification

0 likes · 14 min read

Privacy-Preserving Vertical Federated Graph Neural Network for Node Classification

DataFunSummit

Sep 19, 2022 · Artificial Intelligence

Privacy-Preserving Graph Learning and Recommendation: Techniques, Challenges, and Platform Overview

This article reviews the rapid development of privacy-preserving computation, explains its classification, discusses differential privacy, secure multi‑party computation, federated and split learning, and demonstrates how these techniques can be combined for graph learning and recommendation systems, culminating in a description of the JinZhiTa privacy‑computing platform.

Federated LearningRecommendation systemsdifferential privacy

0 likes · 20 min read

Privacy-Preserving Graph Learning and Recommendation: Techniques, Challenges, and Platform Overview

DataFunTalk

Sep 12, 2022 · Information Security

Understanding Provable Security in Privacy Computing and Differential Privacy

This article explains why privacy‑preserving computation requires provable security, describes how to define security assumptions, illustrates game‑based and simulation‑based proof techniques with Paillier homomorphic encryption and OT examples, and discusses how differential privacy can complement cryptographic guarantees while highlighting practical challenges.

Secure Multiparty Computationcryptographydifferential privacy

0 likes · 15 min read

Understanding Provable Security in Privacy Computing and Differential Privacy

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.

Data SecurityFederated LearningSecure Multiparty Computation

0 likes · 11 min read

Privacy Computing: How Digital Technologies Address Privacy Protection Pain Points

AntTech

May 12, 2022 · Artificial Intelligence

Privacy-Preserving Cross-Domain Recommendation via Differential Privacy and Subspace Embedding

The article reviews a TheWebConf 2022 paper that introduces a two‑stage framework combining differential‑privacy‑based random subspace publishing (using Johnson‑Lindenstrauss and sparse‑aware transforms) with asymmetric deep models to achieve accurate, privacy‑preserving cross‑domain recommendation, and discusses broader differential‑privacy applications.

Recommendation systemsSubspace Embeddingcross-domain recommendation

0 likes · 9 min read

Privacy-Preserving Cross-Domain Recommendation via Differential Privacy and Subspace Embedding

DataFunSummit

Aug 20, 2021 · Artificial Intelligence

Data Privacy and Differential Privacy Techniques in Machine Learning

This article reviews recent data privacy challenges in machine learning, explains the distinction between privacy and security, presents classic attacks and anonymization methods such as K‑anonymity, L‑diversity and T‑closeness, and details differential privacy techniques and their impact on model performance.

anonymizationdata privacydifferential privacy

0 likes · 17 min read

Data Privacy and Differential Privacy Techniques in Machine Learning

DataFunTalk

Dec 18, 2020 · Artificial Intelligence

Federated Learning and Secure Multi‑Party Computation: Concepts, Security Challenges, and Practical Solutions

This article explains the evolution of federated learning, contrasts Google’s cross‑device horizontal approach with China’s cross‑silo vertical implementations, analyzes their security vulnerabilities, and demonstrates how secure multi‑party computation—including differential privacy, secure aggregation, and secret‑sharing techniques—can address these challenges while highlighting performance trade‑offs.

Federated Learningcross-silodifferential privacy

0 likes · 18 min read

Federated Learning and Secure Multi‑Party Computation: Concepts, Security Challenges, and Practical Solutions

DataFunSummit

Dec 16, 2020 · Artificial Intelligence

Federated Learning vs Secure Multi‑Party Computation: Concepts, Challenges, and Alibaba’s Solutions

This article explains the fundamentals of federated learning and secure multi‑party computation, compares their security and performance trade‑offs, discusses the differences between Google’s cross‑device FL and China’s cross‑silo FL, and presents Alibaba’s recent advances and practical solutions for privacy‑preserving collaborative modeling.

Federated Learningcross-silodifferential privacy

0 likes · 18 min read

Federated Learning vs Secure Multi‑Party Computation: Concepts, Challenges, and Alibaba’s Solutions

AntTech

Aug 18, 2020 · Artificial Intelligence

Shared Intelligence vs. Federated Learning: Techniques, Challenges, and Ant Group’s Practical Experience

The article compares shared intelligence and federated learning, examines privacy‑preserving techniques such as MPC, TEE, and differential privacy, discusses gradient‑inversion attacks and their mitigations, and presents Ant Group’s end‑to‑end system design and real‑world deployments in finance.

AI securityAnt GroupFederated Learning

0 likes · 22 min read

Shared Intelligence vs. Federated Learning: Techniques, Challenges, and Ant Group’s Practical Experience

AntTech

Jul 17, 2020 · Artificial Intelligence

Privacy-Preserving Shared Intelligence: Secure AI Techniques for Financial Services

This article outlines how Ant Group’s shared‑intelligence platform combines differential privacy, trusted execution environments, and secure multi‑party computation to enable privacy‑preserving AI and data collaboration across financial scenarios, addressing regulatory demands, technical challenges, and real‑world deployment cases.

Data SharingFinancial AIdifferential privacy

0 likes · 19 min read

Privacy-Preserving Shared Intelligence: Secure AI Techniques for Financial Services

AntTech

Jun 2, 2020 · Artificial Intelligence

Privacy-Preserving Machine Learning Workshop at CCS 2020 (Ant Shared Intelligence)

The Ant Shared Intelligence workshop at ACM CCS 2020 invites researchers and practitioners to submit short papers on privacy‑preserving machine learning techniques such as secure multi‑party computation, homomorphic encryption, differential privacy, federated learning, and related applications, with a submission deadline of June 21, 2020.

AI securityCCS2020Federated Learning

0 likes · 5 min read

Privacy-Preserving Machine Learning Workshop at CCS 2020 (Ant Shared Intelligence)

DataFunTalk

Apr 17, 2020 · Artificial Intelligence

Data Privacy and Differential Privacy Techniques for Machine Learning

The article reviews the growing importance of data privacy in machine learning, explains privacy concepts and attack vectors, and details anonymization methods such as k‑anonymity, l‑diversity, t‑closeness, as well as differential privacy techniques and their practical applications.

data privacydifferential privacyinformation security

0 likes · 13 min read

Data Privacy and Differential Privacy Techniques for Machine Learning