You can yak but you can't hide

Localizing anonymous social network users

Minhui Xue, Cameron Ballard, Kelvin Liu, Carson Nemelka, Yanqiu Wu, Keith Ross, Haifeng Qian

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    The recent growth of anonymous social network services - such as 4chan, Whisper, and Yik Yak - has brought online anonymity into the spotlight. For these services to function properly, the integrity of user anonymity must be preserved. If an attacker can determine the physical location from where an anonymous message was sent, then the attacker can potentially use side information (for example, knowledge of who lives at the location) to de-Anonymize the sender of the message. In this paper, we investigate whether the popular anonymous social media application Yik Yak is susceptible to localization attacks, thereby putting user anonymity at risk. The problem is challenging because Yik Yak application does not provide information about distances between user and message origins or any other message location information. We provide a comprehensive data collection and supervised machine learning methodology that does not require any reverse engineering of the Yik Yak protocol, is fully automated, and can be remotely run from anywhere. We show that we can accurately predict the locations of messages up to a small average error of 106 meters. We also devise an experiment where each message emanates from one of nine dorm colleges on the University of California Santa Cruz campus. We are able to determine the correct dorm college that generated each message 100% of the time.

    Original languageEnglish (US)
    Title of host publicationIMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference
    PublisherAssociation for Computing Machinery
    Pages25-31
    Number of pages7
    Volume14-16-November-2016
    ISBN (Electronic)9781450345262
    DOIs
    StatePublished - Nov 14 2016
    Event2016 ACM Internet Measurement Conference, IMC 2016 - Santa Monica, United States
    Duration: Nov 14 2016Nov 16 2016

    Other

    Other2016 ACM Internet Measurement Conference, IMC 2016
    CountryUnited States
    CitySanta Monica
    Period11/14/1611/16/16

    Fingerprint

    Reverse engineering
    Learning systems
    Experiments

    Keywords

    • Anonymous Social Networks
    • Localization Attack
    • Machine Learning Inference
    • Yik Yak

    ASJC Scopus subject areas

    • Software
    • Computer Networks and Communications

    Cite this

    Xue, M., Ballard, C., Liu, K., Nemelka, C., Wu, Y., Ross, K., & Qian, H. (2016). You can yak but you can't hide: Localizing anonymous social network users. In IMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference (Vol. 14-16-November-2016, pp. 25-31). Association for Computing Machinery. https://doi.org/10.1145/2987443.2987449

    You can yak but you can't hide : Localizing anonymous social network users. / Xue, Minhui; Ballard, Cameron; Liu, Kelvin; Nemelka, Carson; Wu, Yanqiu; Ross, Keith; Qian, Haifeng.

    IMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference. Vol. 14-16-November-2016 Association for Computing Machinery, 2016. p. 25-31.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Xue, M, Ballard, C, Liu, K, Nemelka, C, Wu, Y, Ross, K & Qian, H 2016, You can yak but you can't hide: Localizing anonymous social network users. in IMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference. vol. 14-16-November-2016, Association for Computing Machinery, pp. 25-31, 2016 ACM Internet Measurement Conference, IMC 2016, Santa Monica, United States, 11/14/16. https://doi.org/10.1145/2987443.2987449
    Xue M, Ballard C, Liu K, Nemelka C, Wu Y, Ross K et al. You can yak but you can't hide: Localizing anonymous social network users. In IMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference. Vol. 14-16-November-2016. Association for Computing Machinery. 2016. p. 25-31 https://doi.org/10.1145/2987443.2987449
    Xue, Minhui ; Ballard, Cameron ; Liu, Kelvin ; Nemelka, Carson ; Wu, Yanqiu ; Ross, Keith ; Qian, Haifeng. / You can yak but you can't hide : Localizing anonymous social network users. IMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference. Vol. 14-16-November-2016 Association for Computing Machinery, 2016. pp. 25-31
    @inproceedings{592214b8fc0e4cc78e80c3543dd82a3c,
    title = "You can yak but you can't hide: Localizing anonymous social network users",
    abstract = "The recent growth of anonymous social network services - such as 4chan, Whisper, and Yik Yak - has brought online anonymity into the spotlight. For these services to function properly, the integrity of user anonymity must be preserved. If an attacker can determine the physical location from where an anonymous message was sent, then the attacker can potentially use side information (for example, knowledge of who lives at the location) to de-Anonymize the sender of the message. In this paper, we investigate whether the popular anonymous social media application Yik Yak is susceptible to localization attacks, thereby putting user anonymity at risk. The problem is challenging because Yik Yak application does not provide information about distances between user and message origins or any other message location information. We provide a comprehensive data collection and supervised machine learning methodology that does not require any reverse engineering of the Yik Yak protocol, is fully automated, and can be remotely run from anywhere. We show that we can accurately predict the locations of messages up to a small average error of 106 meters. We also devise an experiment where each message emanates from one of nine dorm colleges on the University of California Santa Cruz campus. We are able to determine the correct dorm college that generated each message 100{\%} of the time.",
    keywords = "Anonymous Social Networks, Localization Attack, Machine Learning Inference, Yik Yak",
    author = "Minhui Xue and Cameron Ballard and Kelvin Liu and Carson Nemelka and Yanqiu Wu and Keith Ross and Haifeng Qian",
    year = "2016",
    month = "11",
    day = "14",
    doi = "10.1145/2987443.2987449",
    language = "English (US)",
    volume = "14-16-November-2016",
    pages = "25--31",
    booktitle = "IMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference",
    publisher = "Association for Computing Machinery",

    }

    TY - GEN

    T1 - You can yak but you can't hide

    T2 - Localizing anonymous social network users

    AU - Xue, Minhui

    AU - Ballard, Cameron

    AU - Liu, Kelvin

    AU - Nemelka, Carson

    AU - Wu, Yanqiu

    AU - Ross, Keith

    AU - Qian, Haifeng

    PY - 2016/11/14

    Y1 - 2016/11/14

    N2 - The recent growth of anonymous social network services - such as 4chan, Whisper, and Yik Yak - has brought online anonymity into the spotlight. For these services to function properly, the integrity of user anonymity must be preserved. If an attacker can determine the physical location from where an anonymous message was sent, then the attacker can potentially use side information (for example, knowledge of who lives at the location) to de-Anonymize the sender of the message. In this paper, we investigate whether the popular anonymous social media application Yik Yak is susceptible to localization attacks, thereby putting user anonymity at risk. The problem is challenging because Yik Yak application does not provide information about distances between user and message origins or any other message location information. We provide a comprehensive data collection and supervised machine learning methodology that does not require any reverse engineering of the Yik Yak protocol, is fully automated, and can be remotely run from anywhere. We show that we can accurately predict the locations of messages up to a small average error of 106 meters. We also devise an experiment where each message emanates from one of nine dorm colleges on the University of California Santa Cruz campus. We are able to determine the correct dorm college that generated each message 100% of the time.

    AB - The recent growth of anonymous social network services - such as 4chan, Whisper, and Yik Yak - has brought online anonymity into the spotlight. For these services to function properly, the integrity of user anonymity must be preserved. If an attacker can determine the physical location from where an anonymous message was sent, then the attacker can potentially use side information (for example, knowledge of who lives at the location) to de-Anonymize the sender of the message. In this paper, we investigate whether the popular anonymous social media application Yik Yak is susceptible to localization attacks, thereby putting user anonymity at risk. The problem is challenging because Yik Yak application does not provide information about distances between user and message origins or any other message location information. We provide a comprehensive data collection and supervised machine learning methodology that does not require any reverse engineering of the Yik Yak protocol, is fully automated, and can be remotely run from anywhere. We show that we can accurately predict the locations of messages up to a small average error of 106 meters. We also devise an experiment where each message emanates from one of nine dorm colleges on the University of California Santa Cruz campus. We are able to determine the correct dorm college that generated each message 100% of the time.

    KW - Anonymous Social Networks

    KW - Localization Attack

    KW - Machine Learning Inference

    KW - Yik Yak

    UR - http://www.scopus.com/inward/record.url?scp=85000384325&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85000384325&partnerID=8YFLogxK

    U2 - 10.1145/2987443.2987449

    DO - 10.1145/2987443.2987449

    M3 - Conference contribution

    VL - 14-16-November-2016

    SP - 25

    EP - 31

    BT - IMC 2016 - Proceedings of the 2016 ACM Internet Measurement Conference

    PB - Association for Computing Machinery

    ER -