Alibaba’s Secure Data Hub (SDH) leverages MPC, differential privacy and PPML to create a compliant data clean‑room for advertisers, allowing multi‑party data collaboration without exposing raw user data, thereby enhancing privacy, trust and efficiency in the advertising ecosystem.
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.
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.
The 2024 WAIC Privacy Computing Forum gathered leading experts from academia and industry to discuss how encryption, anonymization, and secure multi‑party computation can protect data privacy while enabling large‑model training and inference, highlighting technical challenges, standards, and emerging solutions across AI, big data, and information security domains.
This article details how Alibaba Mama’s Secure Data Hub (SDH) leverages multi‑party computation, federated learning, and differential privacy to break data silos in advertising, enabling secure cross‑domain user tracking, full‑domain asset analysis, and rapid, privacy‑compliant marketing insights.
In late 2023, Ant Group and academic partners reported fourteen security‑focused research papers accepted at top venues such as USENIX Security, ACM CCS, and USENIX ATC, covering privacy‑preserving computation, secure two‑party GBDT training, macOS kernel fuzzing, privacy‑preserving ML frameworks, Rust OOM handling, and more.
This article presents a detailed case study of how Jiangsu Bank and Ningbo Bank leveraged Ant Group’s multi‑party secure computation platform and the “YinYu” privacy‑computing framework to build joint risk‑control models, enhancing data sharing, security, and approval rates for inclusive finance.
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.
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.
At the 32nd USENIX Security Symposium in Anaheim, Ant Group’s Research Institute sponsored the event and showcased two first‑author papers—one introducing the Squirrel framework for fast, secure two‑party computation of Gradient Boosting Decision Trees, and another proposing an efficient 3‑party protocol for binary circuits in maliciously‑secure DNN inference.
This article introduces the background of open algorithm protocols for heterogeneous platforms, explains the ECDH‑PSI protocol architecture—including handshake and computation phases—and presents practical open‑source implementations and usage steps for privacy‑preserving set intersection.
This article explains Polish (prefix) notation, defines its syntax and lexical rules, and walks through implementing a full parser and evaluator in C using the MPC library, complete with code examples, compilation instructions, and sample interactive sessions.
This guide walks through building a cross‑platform interactive C REPL, covering basic input/output loops, integrating GNU Readline for line editing and history, handling portability with preprocessor directives, and using the MPC library to create a simple Doge language parser.
This article introduces and compares major privacy computing technologies—including MPC, federated learning, TEE, and proxy MPC—evaluating them across security, development cost, operational cost, accuracy, performance, participant scale, control, hardware cost, and trust, and then outlines Ant Group’s privacy computing framework, applications, and standards work.
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.
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.
On March 29, the Beijing FinTech Industry Alliance published two white‑papers—‘Multi‑Party Secure Computation Financial Application Status and Implementation Guide’ and ‘Federated Learning Technology Financial Application White Paper’—detailing policies, standards, case studies, and recommendations for deploying privacy‑preserving AI technologies in the financial sector.
This article surveys the evolution of cryptography from ancient Mesopotamian cipher sticks through classical ciphers, the Enigma machine, modern public‑key systems, and multi‑party computation, then explains the concept, current challenges, and future directions of privacy‑preserving computation technologies.
The paper presents an integrated lateral‑longitudinal control framework for autonomous vehicles that employs a coupled vehicle model and joint constraints within a linear time‑varying model predictive control scheme, yielding a unified performance index and demonstrating more human‑like, balanced tracking of speed, position, and yaw compared with traditional separated controllers.
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.
Alibaba Entertainment’s technical deep‑dive reveals how its Smart Bitrate system leverages big‑data analytics, AI‑driven machine‑learning (including MPC and the Pensieve model) to dynamically select 5‑10‑second video segments, optimizing QoE by balancing high‑definition playback and buffering, achieving 5‑10% more HD viewing and 10‑20% fewer stalls for “The Longest Day in Chang’an.”
This article explains the challenges of traditional key management, compares local and server‑side encryption approaches, and introduces a secure multi‑party computation (MPC) key management system that distributes key fragments across multiple servers to prevent key exposure even if some nodes are compromised.
This article examines the challenges of adaptive bitrate selection in DASH and HLS streaming, compares traditional MPC and buffer‑based methods, and explains how deep reinforcement learning, specifically the Pensieve A3C model, addresses QoE optimization under uncertain network conditions.
