Tagged articles

11 articles

Page 1 of 1

Sep 16, 2025 · Information Security

Cutting-Edge Privacy Tech Unveiled: Gibbon, Panther & PromeFuzz at ACM CCS 2025

At the ACM CCS 2025 live paper showcase, three groundbreaking studies—Gibbon’s fast secure two‑party GBDT training, Panther’s efficient private approximate nearest‑neighbor search on a single server, and PromeFuzz’s knowledge‑driven LLM approach to fuzzing harness generation—are presented, highlighting significant performance and security advances.

LLMMPCapproximate nearest neighbor

0 likes · 8 min read

Cutting-Edge Privacy Tech Unveiled: Gibbon, Panther & PromeFuzz at ACM CCS 2025

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

Aug 7, 2025 · Information Security

USENIX Security 2025 Live: Crypto DoS, Secure Graph Analysis, Video Forensics

The upcoming USENIX Security 2025 live session in Seattle will showcase three cutting‑edge papers: X.509DoS exposing denial‑of‑service flaws in cryptographic libraries via malformed certificates, GraphAce delivering communication‑efficient two‑party secure graph analysis, and RollingEvidence leveraging rolling‑shutter effects for proactive video forensics.

USENIXcryptographygraph-analysis

0 likes · 7 min read

USENIX Security 2025 Live: Crypto DoS, Secure Graph Analysis, Video Forensics

AntTech

Oct 31, 2024 · Information Security

Coral: A Maliciously Secure Computation Framework for Packed and Mixed Circuits

Ant Group’s cryptography lab introduced Coral, a new maliciously secure multi‑party computation framework that leverages a reverse multiplication‑friendly embedding (RMFE) to efficiently handle packed and mixed circuits, enhancing security from semi‑honest to fully malicious models and delivering practical performance improvements.

Ant GroupMPCMalicious Security

0 likes · 4 min read

Coral: A Maliciously Secure Computation Framework for Packed and Mixed Circuits

AntTech

Sep 25, 2024 · Information Security

Live Presentation of “Coral: Maliciously Secure Computation Framework for Packed and Mixed Circuits” – Paper Highlights and Insights

The announcement introduces the ACM CCS flagship conference, highlights the award‑winning Coral paper that advances malicious secure multi‑party computation with the novel RMFE packing algorithm, and invites readers to a live online session on September 26, 2024 for an in‑depth walkthrough of its theory, technical innovations, and future applications.

ACM CCSCoral FrameworkLive Presentation

0 likes · 4 min read

Live Presentation of “Coral: Maliciously Secure Computation Framework for Packed and Mixed Circuits” – Paper Highlights and Insights

AntTech

Sep 2, 2023 · Information Security

Innovative Cryptographic Technologies and Applications Forum – Session Summaries and Speaker Information

The announcement details a September 7 forum hosted by the China Cryptology Society, featuring eight technical talks on cutting‑edge cryptographic and data‑security technologies—including hardware security, secure GPT inference, volume‑hiding encrypted multi‑maps, end‑to‑same‑end encryption, fully homomorphic encryption databases, dishonest‑majority MPC, active privacy computing, and the Bicoptor protocol—along with speaker biographies and abstracts.

MPCcryptographydata security

0 likes · 15 min read

Innovative Cryptographic Technologies and Applications Forum – Session Summaries and Speaker Information

DataFunSummit

Aug 27, 2023 · Artificial Intelligence

Privacy-Preserving Gradient Boosting Decision Trees via Multi-Party Computation and the Squirrel Framework

This article introduces a privacy-preserving gradient boosting decision tree (GBDT) solution built on multi‑party computation, detailing its background, training steps, the MPC tools used, and the Squirrel framework’s workflow, while discussing performance challenges and experimental results demonstrating scalability to millions of samples.

GBDTMPCSquirrel Framework

0 likes · 9 min read

Privacy-Preserving Gradient Boosting Decision Trees via Multi-Party Computation and the Squirrel Framework

DataFunSummit

Jul 7, 2023 · Information Security

Exploration and Reflections on Interoperability of Privacy Computing

This article presents a comprehensive overview of privacy‑computing interoperability in the financial sector, covering background challenges, the Beijing FinTech Alliance’s collaborative project structure, an industry‑level framework with technical and requirement layers, sub‑topic research results, achieved milestones, and future outlook for standardisation and ecosystem building.

Industry standardsInteroperabilityPrivacy Computing

0 likes · 11 min read

Exploration and Reflections on Interoperability of Privacy Computing

AntTech

Sep 22, 2022 · Artificial Intelligence

SecretFlow Open‑Source Privacy Computing Framework Releases Version 0.7 with Enhanced MPC, Federated Learning, and Performance Optimizations

The SecretFlow privacy‑computing open‑source framework announced its inclusion in the PPCA Open‑Source Working Group and launched version 0.7, adding multi‑party computation, federated learning, infrastructure upgrades, and documentation improvements to advance secure AI and data analytics.

AIFederated LearningMPC

0 likes · 7 min read

SecretFlow Open‑Source Privacy Computing Framework Releases Version 0.7 with Enhanced MPC, Federated Learning, and Performance Optimizations

DataFunSummit

Jul 19, 2022 · Information Security

Fully Homomorphic Encryption: Origins, Development, Applications, and Engineering Challenges in Privacy Computing

This article explores the limitations of current non‑fully homomorphic privacy computing techniques, traces the evolution of fully homomorphic encryption, examines its practical applications in finance and machine learning, and discusses engineering challenges, protocol choices, and implementation considerations for secure data processing.

Financial ApplicationsFully Homomorphic EncryptionPrivacy Computing

0 likes · 16 min read

Fully Homomorphic Encryption: Origins, Development, Applications, and Engineering Challenges in Privacy Computing

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