| Project/Area Number |
18K11294
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 60070:Information security-related
|
|---|
| Research Institution | Shizuoka University |
|---|
Principal Investigator |
OHKI Tetsushi 静岡大学, 情報学部, 准教授 (80537407)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
西垣 正勝 静岡大学, 情報学部, 教授 (20283335)
大塚 玲 情報セキュリティ大学院大学, その他の研究科, 教授 (50415650)
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 生体認証 / バイオメトリクス / なりすまし / セキュリティ / なりすまし攻撃 / なりすまし検知 / Unspoofable Biometrics / 異常検知 / Unspoofable BIometrics / 異常値検知 |
|---|
| Outline of Final Research Achievements |
We have conducted research aimed at developing Unspoofable Biometrics, a secure biometric verification method against all forms of spoofing attacks, including unknown ones. Our pursuit of this goal has been approached from two main perspectives: (1) measures against unknown spoofing attacks, and (2) dealing with unknown spoofing attacks themselves.
With respect to (1), we have succeeded in creating an efficient spoofing detection model with high accuracy while maintaining a minimal model size. Regarding the second aspect, we have considered different attack methods, including the use of model inversion attacks, which allowed us to experimentally evaluate the 'security against unknown attacks' of our method. Our research efforts represent a significant leap in strengthening the security measures of biometric verification systems.
|
| Academic Significance and Societal Importance of the Research Achievements |
なりすまし攻撃の脅威は日々多様化しており，とりわけ未知の攻撃に対する対応能力が求められているが，特定の偽造物の検知を目的とした従来型の検知手法は充分な防御策になり得ていない．本研究では，高次元の複雑な構造を持つ生体情報を確率分布でモデル化可能することで，幅広い未知の攻撃を検知可能な生体認証方式を実現・実証した．人工知能が普及するネットワーク社会では，端末利用者が本人自身である，という真正性を保証することは必須の要件となる.ゆえに，本研究のなりすまし不能性を保証に関する成果は，今後のAI社会インフラ構築に向けた大きな一歩となる.
|
