towards reliable spatial information in lbsns
DESCRIPTION
Towards Reliable Spatial Information in LBSNs. Ke Zhang , Wei Jeng, Francis Fofie , Konstantinos Pelechrinis , Prashant Krishnamurthy University of Pittsburgh ACM LBSN 2012 Pittsburgh, PA. Outline. Problem definition Effects of fake check-ins Fake check-in detection - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/1.jpg)
Ke Zhang, Wei Jeng, Francis Fofie,Konstantinos Pelechrinis, Prashant Krishnamurthy
University of Pittsburgh
ACM LBSN 2012Pittsburgh, PA
Towards Reliable Spatial Information in LBSNs
![Page 2: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/2.jpg)
Outline• Problem definition• Effects of fake check-ins• Fake check-in detection• Conclusion and future work
![Page 3: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/3.jpg)
Location Sharing in LBSN
![Page 4: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/4.jpg)
People can easily forge their whereabouts without proof of the locations…- Alter GPS’s API (FakeLocation)- Bypass localization module to manually check in a different venue than
the actual one
![Page 5: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/5.jpg)
People usually use fake check-in to
Gain real rewards
Mislead others
Gain more virtual rewards
![Page 6: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/6.jpg)
Our Goals and Contribution• Emphasize the effects of fake spatial information
in order to advocate the importance of identifying fake location sharing
• Provide a preliminary system based on location proof to detect fake check-ins
![Page 7: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/7.jpg)
Fake Check-in Leads Monetary Losses…
• Local businesses utilize LBSN as an inexpensive marketing channel for advertisement
• Users can obtain special offers by checking-in to participating venues without their presence
![Page 8: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/8.jpg)
Fake Check-in Results in Degraded Services..
• Noisy data will not guarantee high quality service• Foursquare provides recommendations by
considering check-ins fromo Userso Friends o Venues
• Fake location information degrades the quality of service
![Page 9: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/9.jpg)
Related Efforts• Foursquare provides the “cheater code” to
minimize fake check-ins by imposing additional rules on users’ check-in frequency and speed
• In our work we will utilize the primitives of location proofs
![Page 10: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/10.jpg)
Our Scheme• We consider nearby fake check-ins:
o Users check in to a locale that is nearby even if they are not physically present in it
• Three assumptions: o The number of fake check-ins are less than the true oneso True check-ins are spatially within the venue; fake
check-ins are largely distributed outside the venueo All devices have the same wireless capabilities
![Page 11: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/11.jpg)
Location proofs
User needs to provide location proof along every check-ino Received Signal Strength (RSS) vector measured from nearby
WiFi APs
Check-in points
![Page 12: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/12.jpg)
Location Verification
The LBSN provider utilizes recent k historical proofs provided by users who claims in the venue.
o Apply density clustering to RSS vector space
Check-in points Clusters Noise
![Page 13: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/13.jpg)
Simulation Set Up
• Venues are grouped into blocks of 6 and arranged in a 2D plane separated by streetso 90% of the venues are randomly assigned a WiFi AP
• Users follow the RANK model to decide the next destination to check in
• A user with a fake check-in will be positioned randomly outside the venue
![Page 14: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/14.jpg)
Wireless Channel Model
• Attenuation Factor Model for users to record RSS o : the signal strength at distanceo : path loss exponent o : wall attenuation factoro : number of obstacles along the patho : noise with Gaussian
![Page 15: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/15.jpg)
Evaluation Results
• The performance is better when the wireless channel is stable• In a highly variable environment, our approach still performs
efficiently• Detection works better with smaller number of fake check-ins
![Page 16: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/16.jpg)
Conclusions• We bring the attention to the community on the
effects of fake check-ins by analyzing various possible real-life situations
• We design and evaluate via simulations a prototype detection systemo Density clusteringo Location proofs
![Page 17: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/17.jpg)
Future Directions• Implement our system on real hardware and
examineo Real world performanceo Effect of wireless hardware
• Investigate different – more generic- approaches that do not depend on the assumptions made
![Page 18: Towards Reliable Spatial Information in LBSNs](https://reader036.vdocuments.us/reader036/viewer/2022062315/568163da550346895dd52f6a/html5/thumbnails/18.jpg)
Thank you