Beware of What You Share: Inferring User Locations in Venmo

Xin Yao, Yimin Chen, Rui Zhang, Yanchao Zhang, Yaping Lin

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Mobile payment apps are seeing explosive usage worldwide. This paper focuses on Venmo, a very popular mobile person-to-person (P2P) payment service owned by Paypal. Venmo allows money transfers between users with a mandatory transaction note. More than half of transaction records in Venmo are public information. In this paper, we propose a Multi-Layer Location Inference (MLLI) technique to infer user locations from public transaction records in Venmo. MLLI explores two observations. First, many Venmo transaction notes contain implicit location cues. Second, the types and temporal patterns of user transactions have strong ties to their location closeness. With a large dataset of 2.12M users and 20.23M Venmo transaction records, we show that MLLI can identify the top-1, top-3, and top-5 possible locations for a Venmo user with accuracy up to 50%, 80%, and 90%, respectively. Our results highlight the danger of sharing transaction notes on Venmo or similar mobile payment apps.

Original languageEnglish (US)
JournalIEEE Internet of Things Journal
DOIs
StateAccepted/In press - Jun 5 2018

Fingerprint

Application programs

Keywords

  • Electronic mail
  • Explosives
  • Facebook
  • Internet of Things
  • location inference.
  • Mobile payment
  • Privacy
  • privacy
  • security
  • Text mining
  • Urban areas

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Cite this

Beware of What You Share : Inferring User Locations in Venmo. / Yao, Xin; Chen, Yimin; Zhang, Rui; Zhang, Yanchao; Lin, Yaping.

In: IEEE Internet of Things Journal, 05.06.2018.

Research output: Contribution to journalArticle

@article{badb9c42b1be417f91c3fe9984ff0a48,
title = "Beware of What You Share: Inferring User Locations in Venmo",
abstract = "Mobile payment apps are seeing explosive usage worldwide. This paper focuses on Venmo, a very popular mobile person-to-person (P2P) payment service owned by Paypal. Venmo allows money transfers between users with a mandatory transaction note. More than half of transaction records in Venmo are public information. In this paper, we propose a Multi-Layer Location Inference (MLLI) technique to infer user locations from public transaction records in Venmo. MLLI explores two observations. First, many Venmo transaction notes contain implicit location cues. Second, the types and temporal patterns of user transactions have strong ties to their location closeness. With a large dataset of 2.12M users and 20.23M Venmo transaction records, we show that MLLI can identify the top-1, top-3, and top-5 possible locations for a Venmo user with accuracy up to 50{\%}, 80{\%}, and 90{\%}, respectively. Our results highlight the danger of sharing transaction notes on Venmo or similar mobile payment apps.",
keywords = "Electronic mail, Explosives, Facebook, Internet of Things, location inference., Mobile payment, Privacy, privacy, security, Text mining, Urban areas",
author = "Xin Yao and Yimin Chen and Rui Zhang and Yanchao Zhang and Yaping Lin",
year = "2018",
month = "6",
day = "5",
doi = "10.1109/JIOT.2018.2844218",
language = "English (US)",
journal = "IEEE Internet of Things Journal",
issn = "2327-4662",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Beware of What You Share

T2 - Inferring User Locations in Venmo

AU - Yao, Xin

AU - Chen, Yimin

AU - Zhang, Rui

AU - Zhang, Yanchao

AU - Lin, Yaping

PY - 2018/6/5

Y1 - 2018/6/5

N2 - Mobile payment apps are seeing explosive usage worldwide. This paper focuses on Venmo, a very popular mobile person-to-person (P2P) payment service owned by Paypal. Venmo allows money transfers between users with a mandatory transaction note. More than half of transaction records in Venmo are public information. In this paper, we propose a Multi-Layer Location Inference (MLLI) technique to infer user locations from public transaction records in Venmo. MLLI explores two observations. First, many Venmo transaction notes contain implicit location cues. Second, the types and temporal patterns of user transactions have strong ties to their location closeness. With a large dataset of 2.12M users and 20.23M Venmo transaction records, we show that MLLI can identify the top-1, top-3, and top-5 possible locations for a Venmo user with accuracy up to 50%, 80%, and 90%, respectively. Our results highlight the danger of sharing transaction notes on Venmo or similar mobile payment apps.

AB - Mobile payment apps are seeing explosive usage worldwide. This paper focuses on Venmo, a very popular mobile person-to-person (P2P) payment service owned by Paypal. Venmo allows money transfers between users with a mandatory transaction note. More than half of transaction records in Venmo are public information. In this paper, we propose a Multi-Layer Location Inference (MLLI) technique to infer user locations from public transaction records in Venmo. MLLI explores two observations. First, many Venmo transaction notes contain implicit location cues. Second, the types and temporal patterns of user transactions have strong ties to their location closeness. With a large dataset of 2.12M users and 20.23M Venmo transaction records, we show that MLLI can identify the top-1, top-3, and top-5 possible locations for a Venmo user with accuracy up to 50%, 80%, and 90%, respectively. Our results highlight the danger of sharing transaction notes on Venmo or similar mobile payment apps.

KW - Electronic mail

KW - Explosives

KW - Facebook

KW - Internet of Things

KW - location inference.

KW - Mobile payment

KW - Privacy

KW - privacy

KW - security

KW - Text mining

KW - Urban areas

UR - http://www.scopus.com/inward/record.url?scp=85048166752&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048166752&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2018.2844218

DO - 10.1109/JIOT.2018.2844218

M3 - Article

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

ER -