Artificial Intelligence 5 min read

Ant Group and Tsinghua University’s Distributed Collaborative Risk‑Defense System Wins Zhejiang Provincial Science & Technology Progress Award

The award‑winning distributed collaborative risk‑defense system, developed by Ant Group, Tsinghua University and Alipay, leverages AI, privacy‑preserving computing and graph analytics to achieve real‑time, high‑efficiency detection and invisible, precise control of hidden risks in massive digital transactions, earning top provincial honors and extensive industry adoption.

AntTech
AntTech
AntTech
Ant Group and Tsinghua University’s Distributed Collaborative Risk‑Defense System Wins Zhejiang Provincial Science & Technology Progress Award

On the morning of the award ceremony, the 2022 Zhejiang Provincial Science and Technology Award announced that the project "Distributed Collaborative Risk‑Defense Key Technologies and System for Massive Transactions," jointly completed by Ant Group, Tsinghua University and Alipay, won the First‑Prize of the Zhejiang Provincial Science and Technology Progress Award.

The evaluation committee highlighted the project's high system complexity, difficulty, and strong technical innovation. It introduced the world‑first edge‑cloud distributed collaborative risk‑defense architecture, featuring AI‑based anti‑noise defense models, scalable online dynamic graph contrastive learning, and knowledge‑driven adaptive multi‑dimensional active inquiry risk analysis, all at an internationally leading level.

To address large‑scale network attacks, data‑element security, and rapid detection of multimodal content risks, the team collaborated with Tsinghua University and other institutions to develop the system. The core scientific challenge is abstracted as real‑time, efficient identification and invisible, precise control of hidden unknown risks in massive transactions, achieved through the fusion of AI and security technologies.

Key technical contributions include a privacy‑computing verifiable distributed generic platform that efficiently links multi‑source, multi‑owner data for collaborative security capabilities; an AI model anti‑noise defense framework that resists complex covert forgery attacks; graph‑computing techniques for real‑time, high‑efficiency risk identification in massive relational data; and emotion‑computing and intelligent multimodal human‑machine interaction for proactive risk judgment and control.

The project has yielded substantial academic and industrial outcomes: 129 major domestic and international invention patents, 29 published papers, and six led international/national/industry standards. Its results are deployed across Ant’s massive business scenarios, safeguarding the accounts of 1 billion Alipay users daily, and, through commercialization and open‑source projects, serving over 30 000 ecosystem partners in finance, education, public welfare, and healthcare, as well as supporting digital payment adoption in Belt‑and‑Road countries.

Ant Group Vice President Zhao Wenbiao, a principal contributor, emphasized that security technology is the "ballast" and "accelerant" of the digital economy, and pledged continued investment in foundational research and innovative applications, especially in AI safety.

Over the past 19 years, Ant has built nine security labs for frontier research and collaboration, establishing a self‑developed, validated, end‑to‑end security technology system that has repeatedly won national and provincial awards and secured multiple world‑class competition titles in risk control algorithms and network defense, positioning China’s payment industry security above global standards.

distributed systemsBig Dataprivacy computingAI securityAwardrisk detection
AntTech
Written by

AntTech

Technology is the core driver of Ant's future creation.

0 followers
Reader feedback

How this landed with the community

login Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.