Name
Title | ||
|---|---|---|
A De-anonymization Attack on Geo-Located Data Considering Spatio-temporal Influences. |
Abstract | ||
|---|---|---|
With the wide use of smart phones, a large amount of GPS data are collected, while risks of privacy disclosure are also increasing. The de-anonymization attack is a typical attack which can infer the owner of an anonymous set of mobility traces. However, most existing works only consider spatial influences without considering temporal influences sufficiently. In this paper, we define a User Hidden Markov Model (UHMM) considering spatio-temporal influences, and exploit this model to launch the de-anonymization attack. Moreover, we conduct a set of experiments on a real-world dataset. The results show our approach is more accurate than other methods. |
Year | Venue | Field |
|---|---|---|
2015 | ICICS | Data mining,Gps data,De-anonymization,Computer science,Exploit,Hidden Markov model,Distributed computing |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
12 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rong Wang | 1 | 1 | 1.37 |
| Min Zhang | 2 | 134 | 38.40 |
| Deng-Guo Feng | 3 | 1991 | 190.95 |
| Yanyan Fu | 4 | 1 | 0.69 |
| Zhenyu Chen | 5 | 470 | 25.35 |