Inference Attacks on Location Tracks John Krumm Microsoft Research Redmond, WA USA.

Slides:



Advertisements
Similar presentations
IHSAA 2011 Student Leadership Conference Money Matter$ for IHSAA 2011 Student Leadership Conference.
Advertisements

On the Optimal Placement of Mix Zones Julien Freudiger, Reza Shokri and Jean-Pierre Hubaux PETS, 2009.
The Role of History and Prediction in Data Privacy Kristen LeFevre University of Michigan May 13, 2009.
21-1 Last time Database Security  Data Inference  Statistical Inference  Controls against Inference Multilevel Security Databases  Separation  Integrity.
Virtual Trip Lines for Distributed Privacy-Preserving Traffic Monitoring Baik Hoh, Marco Gruteser WINLAB / ECE Dept., Rutgers University Ryan Herring,
Welcome to Florida International University Online J.O.B.S. Link Applicant Tutorial.
Mobile Resource Manager v2. Core Pillars  Engine - High fuel costs, vehicle maintenance  Productivity - Customers expect increasing levels of service.
Quantifying Location Privacy: The Case of Sporadic Location Exposure Reza Shokri George Theodorakopoulos George Danezis Jean-Pierre Hubaux Jean-Yves Le.
Cyber-Physical Cloud(y) Computing: Good News, Bad News and Looking Forward Haibo Chen.
© Chery F. Kendrick & Kendrick Technical Services.
1 A Distortion-based Metric for Location Privacy Workshop on Privacy in the Electronic Society (WPES), Chicago, IL, USA - November 9, 2009 Reza Shokri.
Do You Trust Your Recommender? An Exploration of Privacy and Trust in Recommender Systems Dan Frankowski, Dan Cosley, Shilad Sen, Tony Lam, Loren Terveen,
FIT3105 Smart card based authentication and identity management Lecture 4.
ITIS 3200 Intro to Security and Privacy Dr. Weichao Wang.
A Survey of Computational Location Privacy John Krumm Microsoft Research Redmond, WA USA.
Computational Location Privacy: Present and Future John Krumm Microsoft Research Redmond, WA USA.
1 User Centered Design and Evaluation. 2 Overview My evaluation experience Why involve users at all? What is a user-centered approach? Evaluation strategies.
Viruses and Spyware. What is a Virus? A virus can be defined as a computer program that can reproduce by changing other programs to include a copy of.
1 Chapter 13: Representing Identity What is identity Different contexts, environments Pseudonymity and anonymity.
Survey Research Questionnaire construction Types of surveys
1 Welcome to the Colgate University Online Employment System Applicant Tutorial.
1 © 2009 University of Wisconsin-Extension, Cooperative Extension, Program Development and Evaluation ONLINE SURVEYS.
OCPA NEIGHBORHOOD WATCH PROGRAM THE OHIO CRIME PREVENTION ASSOCIATION IDENTITY THEFT.
Rutgers: Gayathri Chandrasekaran, Tam Vu, Marco Gruteser, Rich Martin,
Ubiquitous Advertising: the Killer Application for the 21st Century Author: John Krumm Presenter: Anh P. Nguyen
This slide brought to you by What to Do With Thousands of GPS Tracks John Krumm, PhD Microsoft Research Redmond, WA.
1 Preserving Privacy in GPS Traces via Uncertainty-Aware Path Cloaking by: Baik Hoh, Marco Gruteser, Hui Xiong, Ansaf Alrabady ACM CCS '07 Presentation:
Baik Hoh Marco Gruteser Hui Xiong Ansaf Alrabady All images are credited to “ACM” Hoh et al (2007), pp
Social effect: Facebook is a site available to anyone. Many people use it in order to contact friends and relatives from all around the world, and to meet.
ByBrendanMalindaRachael. Electronic Monitoring Electronic monitoring can take many forms, this happens because technology is becoming cheaper and very.
Welcome to And the Rice University Online Job Application Tutorial.
Welcome to the Alaska Statewide System Online Employment System Applicant Tutorial.
1 ______ ___ ____ ___ _____ _______ Seattle City Light Rate Design Outreach November 1, 2013 Summary of Online Survey Results 11/1 Review Panel Discussion.
March 2008 Electronic Billing (EB) Developed by the Department of Developmental Services Developed by the Department of Developmental Services.
Signatures As Threats to Privacy Brian Neil Levine Assistant Professor Dept. of Computer Science UMass Amherst.
PDI TRAINING SESSION: Risk Management Registration for International Travel You will need a CSU EID.
Personal Safety Advice Compiled by DC Jeremy House States of Jersey Police Last Updated 03/02/2011 Not Protectively Marked.
Optimizing Mixing in Pervasive Networks: A Graph-Theoretic Perspective
How to use the Travel Claim Form. When you open the Travel Claim Form you will need to Enable the Content for the form to work correctly. If you receive.
Quantifying Location Privacy Reza Shokri George Theodorakopoulos Jean-Yves Le Boudec Jean-Pierre Hubaux May 2011.
Information Security 2013 Roadshow. Roadshow Outline  Why We Care About Information Security  Safe Computing Recognize a Secure Web Site (HTTPS) How.
Identity Theft  IDENTITY THEFT occurs when someone wrongfully acquires and uses a consumer’s personal identification, credit, or account information.
1 Welcome to HSPA Online. 2 Measurement Incorporated Partnering with NJDOE & New Jersey School Districts.
Research and Analysis Methods October 5, Surveys Electronic vs. Paper Surveys –Electronic: very efficient but requires users willing to take them;
Toward Community Sensing Andreas Krause Carnegie Mellon University Joint work with Eric Horvitz, Aman Kansal, Feng Zhao Microsoft Research Information.
Microsoft ® Office Access ™ 2007 Training Datasheets I: Create a table by entering data ICT Staff Development presents:
Deducing Mode and Purpose from GPS Data Peter Stopher, Jun Zhang and Eoin Clifford Institute of Transport and Logistics Studies The University of Sydney.
Road pricing. Why ? What is it ? How might it be introduced ? Where and when ? How might it work? Why ? What is it ? How might it be introduced ? Where.
Accuracy Characterization for Metropolitan-scale Wi-Fi Localization Yu-Chung Cheng (UCSD, Intel Research) Yatin Chawathe (Intel Research) Anthony LaMarca.
Elastic Pathing: Your Speed Is Enough to Track You Presented by Ali.
Alastair R. Beresford Frank Stajano University of Cambridge Presented by Arcadiy Kantor — CS4440 September 13, 2007.
Audio Location Accurate Low-Cost Location Sensing James Scott Intel Research Cambridge Boris Dragovic Intern in 2004 at Intel Research Cambridge Studying.
Alert Message Formats for SAR Points of Contact (SPOCs) - Overview and Interpretation - Tom Griffin, USMCC Senior Systems Analyst U.N./USA Training Course.
Preserving Privacy in GPS Traces via Uncertainty- Aware Path Cloaking Baik Hoh, Marco Gruteser, Hui Xiong, Ansaf Alrabady Presented by Joseph T. Meyerowitz.
Microsoft Research Faculty Summit John Krumm Microsoft Research Redmond, WA.
Virtual Trip Lines for Distributed Privacy- Preserving Traffic Monitoring Baik Hoh et al. MobiSys08 Slides based on Dr. Hoh’s MobiSys presentation.
ONE® Pages Training Presentation North York General Hospital.
Preserving Privacy GPS Traces via Uncertainty-Aware Path Cloaking Baik Hoh, Marco Gruteser, Hui Xiong, Ansaf Alrabady Presenter:Yao Lu ECE 256, Spring.
When I Grow Up! WebQuest for 6 th grade students Created by: Sandra Ball Northampton Community College.
Campus Mail Services New USPS Requirement USPS IMpb Solution (Intelligent Mail Parcel Barcode) EMS WEBVIEW SHIPPING.
THIS TRAINING IS REQUIRED IN ORDER TO OBTAIN SECURITY TO INITIATE HIRING PACKETS FOR NEW EMPLOYEES. Hire Xpress User’s Training NAU’s Automated Hiring.
Media Relations Insa Ben Said Dia. CONTENTS How to write a press release 1 Why being concerned about Media Relations as Unionists? Invitations to the.
Privacy Vulnerability of Published Anonymous Mobility Traces Chris Y. T. Ma, David K. Y. Yau, Nung Kwan Yip (Purdue University) Nageswara S. V. Rao (Oak.
Unlinking Private Data
COMPSCI 720 Security for Smart-devices Tracking Mobile Web Users Through Motion Sensors: Attacks and Defenses [1] Harry Jackson hjac660 [1] Das, Anupam,
Welcome to CS 1010! Algorithmic Problem Solving.
ONE® Pages Training Presentation
A Unified Framework for Location Privacy
Mobile Registration App Training Guide for OPO Staffers
Presentation transcript:

Inference Attacks on Location Tracks John Krumm Microsoft Research Redmond, WA USA

Questions to Answer Do anonymized location tracks reveal your identity? If so, how much data corruption will protect you? theoryexperiment

Motivation – Why Send Your Location? Congestion Pricing Location Based Services Pay As You Drive (PAYD) Insurance Collaborative Traffic Probes (DASH) Research (London OpenStreetMap) Nancy Krumm (Mom) Moving out of basement soon? Your father and I are wondering if you plan to

GPS Data Microsoft Multiperson Location Survey (MSMLS) 55 GPS receivers 226 subjects 95,000 miles 153,000 kilometers 12,418 trips Home addresses & demographic data Greater Seattle Seattle DowntownClose-up Garmin Geko 201 $115 10,000 point memory median recording interval 6 seconds 63 meters

People Don’t Care About Location Privacy (1) Danezis, G., S. Lewis, and R. Anderson. How Much is Location Privacy Worth? in Fourth Workshop on the Economics of Information Security Harvard University. 74 U. Cambridge CS students Would accept £10 to reveal 28 days of measured locations (£20 for commercial use) (1) 226 Microsoft employees 14 days of GPS tracks in return for 1 in 100 chance for $200 MP3 player 62 Microsoft employees Only 21% insisted on not sharing GPS data outside 11 with location-sensitive message service in Seattle Privacy concerns fairly light (2) (2) Iachello, G., et al. Control, Deception, and Communication: Evaluating the Deployment of a Location-Enhanced Messaging Service. in UbiComp 2005: Ubiquitous Computing Tokyo, Japan. (3) Kaasinen, E., User Needs for Location- Aware Mobile Services. Personal and Ubiquitous Computing, (1): p Finland interviews on location-aware services “It did not occur to most of the interviewees that they could be located while using the service.” (3) Seattle Area Probation Authority Probation check-in on May 15 Mr. Krumm – sure hope to find you at home

Documented Privacy Leaks How Cell Phone Helped Cops Nail Key Murder Suspect – Secret “Pings” that Gave Bouncer Away New York, NY, March 15, 2006 Stalker Victims Should Check For GPS Milwaukee, WI, February 6, 2003 A Face Is Exposed for AOL Searcher No New York, NY, August 9, 2006 Real time celebrity sightings

Pseudonimity for Location Tracks Pseudonimity Replace owner name of each point with untraceable ID One unique ID for each owner Example “Larry Page” → “yellow” “Bill Gates” → “red” eBay You’ve won item #245632! Darth Vader costume and light saber will be

Attack Outline Pseudonomized GPS tracks Infer home location Reverse white pages for identity

GPS Tracks → Home Location Algorithm 1 Last Destination – median of last destination before 3 a.m. Median error = 60.7 meters Netflix.com Netflix movie shipment “Velvety Vixens from Venus II” has shipped as

GPS Tracks → Home Location Algorithm 2 Weighted Median – median of all points, weighted by time spent at point (no trip segmentation required) Median error = 66.6 meters

GPS Tracks → Home Location Algorithm 3 Largest Cluster – cluster points, take median of cluster with most points Median error = 66.6 meters

GPS Tracks → Home Location Algorithm 4 Best Time – location at time with maximum probability of being home Median error = meters (!) Microsoft Human Resources Termination package In light of your most recent performance review

Why Not More Accurate? GPS interval – 6 seconds and 63 meters GPS satellite acquisition -- ≈45 seconds on cold start, time to drive 300 meters at 15 mph Covered parking – no GPS signal Distant parking – far from home covered parkingdistant parking

GPS Tracks → Identity? Windows Live Search reverse white pages lookup (free API at Hunter Randall, M.D. Diagnosis of red sore John – have you been involved recently with

Identification GPS Tracks (172 people) Home Location (61 meters) Home Address (12%) Identity (5%) MapPoint Web Service reverse geocoding Windows Live Search reverse white pages AlgorithmCorrect out of 172Percent Correct Last Destination84.7% Weighted Median95.2% Largest Cluster95.2% Best Time21.2% Ellen Krumm Home’s a mess! Would it kill you to take out the garbage?

Why Not Better? Multiunit buildings Outdated white pages Poor geocoding Ela Dramowicz, “Three Standard Geocoding Methods”, Directions Magazine, October 24, Toupees for Men Awaiting payment We may be forced to repossess your hairpiece

Similar Study Hoh, Gruteser, Xiong, Alrabady, Enhancing Security and Privacy in Traffic-Monitoring Systems, in IEEE Pervasive Computing p volunteer drivers in Detroit, MI area Cluster destinations to find home location arrive 4 p.m. to midnight must be in residential area Manual inspection on home location (no knowledge of drivers’ actual home address) 85% of homes found

Easy Way to Fix Privacy Leak? Location Privacy Protection Methods 1.Regulatory strategies – based on rules 2.Privacy policies – based on trust 3.Anonymity – e.g. pseudonymity 4.Obfuscation – obscure the data Duckham, M. and L. Kulik, Location Privacy and Location- Aware Computing, in Dynamic & Mobile GIS: Investigating Change in Space and Time, J. Drummond, et al., Editors. 2006, CRC Press: Boca Raton, FL. Burger King – Redmond, WA Your job application After evaluating your application, we regret

Obfuscation Techniques (Duckham and Kulik, 2006) Spatial Cloaking 1,2 – confuse with other people Noise 3 – add noise to measurements Rounding 3 – discretize measurements Vagueness 4 – “home”, “work”, “school”, “mall” Dropped Samples 5 – skip measurements 1 Gruteser, M. and D. Grunwald Beresford, A.R. and F. Stajano Agrawal, R. and R. Srikant Consolvo, S., et al Hoh, B., et al

Countermeasure: Add Noise originalσ= 50 meters noise added Effect of added noise on address-finding rate Christine Krumm Minivan insurance card Hey Dad, I thought the insurance card was in

Countermeasure: Discretize originalsnap to 50 meter grid Effect of discretization on address-finding rate

Countermeasure: Cloak Home 1.Pick a random circle center within “r” meters of home 2.Delete all points in circle with radius “R” Toronto Marriott at Eaton Centre Attention please, attention please Trained personnel hope you have a restful stay

Conclusions Privacy Leak from Location Data – Can infer identity: GPS → Home → Identity – Best was 5% – 5% is lower bound, evil geniuses will do better Obfuscation Countermeasures – Need lots of corruption to approach zero risk

Next Steps How does data corruption affect applications?

End originalnoise discretizecloak reverse white pages Professor Gerald Stark Your talk at Pervasive First of all, the popups weren’t funny.