towards privacy-sensitive participatory sensing
DESCRIPTION
Towards Privacy-Sensitive Participatory Sensing. K.L. Huang, S. S. Kanhere and W. Hu Presented by Richard Lin Zhou. Overview. Significance of Privacy Sensitiveness Earlier Developments (Tessellation) Microaggregation Combining both techniques (Hybrid V-MDAV ) Gaussian Perturbation. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/1.jpg)
TOWARDS PRIVACY-SENSITIVE PARTICIPATORY SENSINGK.L. Huang, S. S. Kanhere and W. HuPresented by Richard Lin Zhou
![Page 2: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/2.jpg)
OVERVIEW Significance of Privacy Sensitiveness Earlier Developments (Tessellation) Microaggregation Combining both techniques (Hybrid V-MDAV) Gaussian Perturbation
![Page 3: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/3.jpg)
SIGNIFICANCE OF PRIVACY-SENSITIVENESS Participatory sensing application requires
personal information Relies on altruistic participation Users needs to be assured of their privacy
not being violated
![Page 4: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/4.jpg)
EARLIER DEVELOPMENTS Anonysense (Tessellation)
Presented earlier by L. Tussing Divide users into groups of tiles. Generalization guided by the principle of k-
anonymity.
![Page 5: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/5.jpg)
LIMITATIONS OF TESSELLATION Not suitable for application that require fine-
grained information. Application that collects traffic information
Reports generated for different intersections associated with the same Tile ID.
Not useful for information purposes.
![Page 6: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/6.jpg)
MODIFIED TESSELLATION To allow calculation of distance by points Report the center point of the Tile rather than
Tile ID
![Page 7: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/7.jpg)
LIMITATIONS OF TESSELLATION Petrol Watch
![Page 8: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/8.jpg)
MICROAGGREGATION Used for implementing database disclosure
control No generalization nor suppression of the
values of an attribute Replaces the values with the mean of the
Equivalence Classes (EC) in which the record is found
Member similarities often quantified by the Information Loss (IL) metric
Maximum Distance to Average Vector (MDAV) widely recognized as one of the most efficient heuristics to date.
![Page 9: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/9.jpg)
MAXIMUM DISTANCE TO AVERAGE VECTOR (MDAV) ALGORITHM Fixed Sized Algorithm Variable class size version: V-MDAV Involves two principal successive operations
1. Equivalence Class (EC) generation Clusters users who exhibit high geographic
similarities in groups of k Ensures that k-anonymity is enforced
2. EC extension Merge geographically close users with an existing EC
![Page 10: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/10.jpg)
V-MDAV Petrol Watch
![Page 11: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/11.jpg)
CASES THAT V-MDAV NOT PERFORMING
![Page 12: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/12.jpg)
TESSELLATION V.S. M-MDAV V-MDAV enables the application to make
better decisions when the user distribution across different areas is consistent, as in
In areas with dense distribution of users, Tessellation performs better.
So which to use?
![Page 13: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/13.jpg)
COMBINE TESSELLATION AND V-MDAV Hybrid V-MDAV
If the number of users within the cell exceeds k, then MT is used
Otherwise, the algorithm switches to V-MDAV
![Page 14: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/14.jpg)
EXPERIMENTS
![Page 15: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/15.jpg)
EVALUATION
![Page 16: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/16.jpg)
GAUSSIAN INPUT PERTURBATION Previous methods assume the existence of a
trusted third-party server, which is aware of the true locations of the participating users.
If this server is compromised, the users’ privacy is at risk
Solution: Adding a random Gaussian noise with mean μ
and standard deviation σ to the X and Y Perturbed location:
p: scaling variable
![Page 17: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/17.jpg)
IMPACT OF GAUSSIAN PERTURBATION
![Page 18: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/18.jpg)
IMPACT OF GAUSSIAN PERTURBATION
![Page 19: Towards Privacy-Sensitive Participatory Sensing](https://reader036.vdocuments.site/reader036/viewer/2022062520/568163ba550346895dd4d0b1/html5/thumbnails/19.jpg)
CONCLUSION Hybrid V-MDAV combines the positive
aspects of tessellation and microaggregation. Improves Positive Identification by 100% Decreases Information Loss by 40% Gaussian Perturbation added extra layer of
privacy protection