Study on the Practical Implementation of Browser Tracking Technology in Mobile Environments
| Project/Area Number |
18K11305
|
|---|
| 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 | Meiji University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2020: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2019: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2018: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | 情報セキュリティ / ネット不正検知 / ブラウザフィンガープリント / アトリビューション / ブラウザ追跡 / Web追跡 / サイバーアトリビューション / Webトラッキング / プライバシー / モバイルトラッキング / ブラウザトラッキング / セキュリティ / モバイル / 識別 / プライバシ |
|---|
| Outline of Final Research Achievements |
Browser fingerprinting technology (FP technology) is a technique that identifies browsers on the server side by utilizing the information that a browser can use when accessing a web server. FP technology has applications in the detection of online fraudulent activities, making it a highly anticipated technology socially. However, not only are fraudsters taking countermeasures against FP technology, but browser vendors are also strengthening their tracking features, making identification increasingly difficult. In this study, we conducted research on more advanced methods, such as applying machine learning.
In this research, we conducted a large-scale experiment (with over 20 million accesses and 600,000 different devices), achieving results of 0.99 or higher in precision, recall, accuracy, and F1 score. Furthermore, we carried out experiments using an innovative method that leverages clustering, anticipating situations where obtaining supervised labels is challenging.
|
| Academic Significance and Societal Importance of the Research Achievements |
大規模な実験 （総アクセス数2千万以上のアクセス、60万種 類の端末）で、precision、recall、accuracy、F1のいずれもで、0.99以上の結果を得ている。また、FP技術は、応用としてネット不正検知に用いることができる。たとえば、オンラインバンクなどにおいて、正規の口座へのアクセス情報を不正に入手して、不正行為を働く際、その行為者の特定などに用いることができる。本研究では、ネット銀行との試みとして、実データを用いた実証実験も行った。
|
Report
(6 results)
Research Products
(54 results)
