IdentityLink
Authors:
Open Access
- 13 September 2014
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 529-539
Abstract
Mobile devices have become people's indispensable companion, since they allow each individual to be constantly connected with the outside world. In order to keep connected, the devices periodically send out data, which reveal some information about the device owner. Data sent by these devices can be captured by any external observer. Since the observer can observe only the wireless data, the actual person using the device is unknown. In this work, we propose IdentityLink, an approach leveraging the captured wireless data and computer vision to infer the user-device links, i.e., inferring which device is carried by which user. Knowing the user-device links opens up new opportunities for applications such as identifying unauthorized personnel in enterprises or finding criminals by law enforcement. By conducting experiments in a realistic scenario, we demonstrate how IdentityLink can be effectively applied to real practice.Keywords
Funding Information
- Division of Information and Intelligent Systems (IIS-1344768)
This publication has 15 references indexed in Scilit:
- A Review on Video-Based Human Activity RecognitionComputers, 2013
- Who do you sync you are?2013
- NetworkProfiler: Towards automatic fingerprinting of Android apps2013
- Human detection using depth information by Kinect2011
- Appearance-based person reidentification in camera networks: problem overview and current approachesJournal of Ambient Intelligence and Humanized Computing, 2011
- Tasking networked CCTV cameras and mobile phones to identify and localize multiple people2010
- A survey on vision-based human action recognitionImage and Vision Computing, 2010
- Inferring the source of encrypted HTTP connections2006
- Analyzing features for activity recognition2005
- Detection of Loitering Individuals in Public Transportation AreasIEEE Transactions on Intelligent Transportation Systems, 2005