Portrait of Yiming Li
Photo: Tsinghua University · Publisher-directed editorial display; source copyright retained

FigureAsia 35 Under 35 · Science

Yiming Li

Age 29 · AI security and data rights · China / Singapore

AI-security researcher turning model ownership into a testable technical claim without planting a label-changing backdoor.

Approximate age at the edition eligibility date
29
Field
Computer science
Country or region
China / Singapore
FigureAsia U35 Assessment
80.6 / 100

Career and documented record

Yiming Li works on a question with immediate commercial consequences: how a developer can show that a neural network was copied without planting a backdoor in the original model. In June 2025, IEEE Transactions on Pattern Analysis and Machine Intelligence published MOVE, with Li first on the eight-author paper, in volume 47, issue 6, pages 4734–4751.

MOVE applies style transfer to a small share of training images while retaining their labels, then trains a meta-classifier to test whether a suspect model carries those defender-selected external features. The journal version extends the team's 2022 AAAI work from white-box to black-box verification and adds adaptive-attack analysis and a broader experimental record.

Li is now a Research Fellow at Nanyang Technological University, where he frames his programme around responsible and sustainable AI, AI risk management and copyright protection. MOVE provides evidence under tested image-classification threat models; it is neither a legal finding of infringement nor a universal guarantee against model theft.

Why Yiming Li is on the list

Li is selected for turning model ownership from a policy assertion into a measurable security problem. MOVE addresses copying without modifying class labels, and its first authorship makes his responsibility legible.

The 2025–26 record

MOVE in IEEE TPAMI

First-listed author of the eight-author journal paper in volume 47, issue 6, pages 4734–4751; DOI 10.1109/TPAMI.2025.3546223.

Ownership verification without a backdoor

Embedded defender-selected external features through label-preserving style transfer and tested for their presence with a meta-classifier.

Expanded threat model

Extended the earlier AAAI study to white-box and black-box settings, with adaptive-attack analysis and broader experiments.

The work in its field

Neural-network ownership is difficult to prove because weights can be hidden, models can be modified and conventional backdoor watermarks may compromise normal behaviour. A useful method must survive realistic access limits without creating a new security risk.

Assessment breakdown

80.6out of 100

01

Substantive 2025–2026 contribution

15 / 20

First-listed author of the eight-author journal paper in volume 47, issue 6, pages 4734–4751; DOI 10.1109/TPAMI.2025.3546223.

02

Verified scientific impact

11.3 / 15

A first-authored TPAMI result turns AI ownership from a policy assertion into a measurable security problem while avoiding the label-changing backdoors used by many earlier watermarking schemes.

03

Originality and distinction

8.2 / 10

The distinction lies in using label-preserving style transfer and a meta-classifier to verify copied-model ownership without inserting a conventional backdoor.

04

Field influence

8.3 / 10

Researchers in ai security and data rights now have a stronger result to test, extend or challenge because of this contribution.

05

Individual agency

8.2 / 10

Li is the first-listed author of the eight-author TPAMI paper. The evidence supports lead authorship of the journal extension, not sole invention.

06

Durability and trajectory

4.3 / 5

MOVE extends Li's earlier AAAI work into a fuller journal record and sits inside his continuing NTU programme on AI risk and copyright protection.

07

Asian significance and global relevance

4.3 / 5

Chinese computer scientist educated at Tsinghua and Zhejiang Universities and now working in Singapore.

08

Evidential validity and reproducibility

6.7 / 8

The paper tests white-box and black-box settings and adaptive attacks; no claim of universal robustness or legal proof is made.

09

Advance in scientific knowledge

5.8 / 7

MOVE shows how externally selected visual features can carry a detectable ownership signal without changing training labels.

10

Translational or methodological utility

4.3 / 5

The method gives developers a technical route to investigate suspected model copying when weights or training records are unavailable.

11

Responsible research stewardship

4.2 / 5

The profile separates experimental ownership evidence from legal judgement and retains the limits of the tested threat models.

Evidence and attribution

Material claims on this page are supported by the edition’s evidence record. FigureAsia tests age, identity, role, result and individual attribution before publication. Public profiles present the reported record; supporting documentation is retained for accuracy review and corrections.

Achievement records
4
Assessment window
2025–26
Editorial status
Included in the 2026 FigureAsia 35 Under 35 edition

Rights and credit

The portrait is published under the rights basis recorded for this edition. Third-party ownership and reuse restrictions remain in force.

Publication status
Published under a documented rights basis
Credit
Tsinghua University
Licence
Publisher-directed editorial display; source copyright retained
Portrait source and credit