| Project/Area Number |
26880030
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Information security
|
|---|
| Research Institution | National Institute of Advanced Industrial Science and Technology |
|---|
Principal Investigator |
Murakami Takao 国立研究開発法人産業技術総合研究所, 情報技術研究部門, 研究員 (80587981)
|
|---|
| Project Period (FY) |
2014-08-29 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 位置情報プライバシー / 個人識別攻撃 / マルコフモデル / テンソル分解 / グループスパース正則化 / 匿名化 / 曖昧化 / 欠損位置情報 / Viterbiアルゴリズム |
|---|
| Outline of Final Research Achievements |
In this research project, we focused on de-anonymization of mobility traces as a privacy risk that cannot be mitigated using only anonymous authentication (or anonymous biometric authentication), which is widely studied to protect privacy in the era of Big Data. Specifically, we considered the fact that the number of training traces available to an adversary is very small, and proposed a learning method of personalized transition matrices using tensor factorization and group sparsity regularization. As a defense against this kind of attack, we proposed a location obfuscation method that minimizes the region size while keeping the attack success probability less than a required value. We showed the effectiveness of our proposed methods through experimental evaluation using real datasets.
|
