Attribute Inference Attacks in Online Social Networks
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
We propose new privacy attacks to infer attributes (e.g., locations, occupations, and interests) of online social network users. Our attacks leverage seemingly innocent user information that is publicly available in online social networks to infer missing attributes of targeted users. Given the increasing availability of (seemingly innocent) user information online, our results have serious implications for Internet privacy—private attributes can be inferred from users’ publicly available data unless we take steps to protect users from such inference attacks. To infer attributes of a targeted user, existing inference attacks leverage either the user’s publicly available social friends or the user’s behavioral records (e.g., the web pages that the user has liked on Facebook, the apps that the user has reviewed on Google Play), but not both. As we will show, such inference attacks achieve limited success rates. However, the problem becomes qualitatively different if we consider both social friends and behavioral records. To address this challenge, we develop a novel model to integrate social friends and behavioral records, and design new attacks based on our model. We theoretically and experimentally demonstrate the effectiveness of our attacks. For instance, we observe that, in a real-world large-scale dataset with 1.1 million users, our attack can correctly infer the cities a user lived in for 57% of the users; via confidence estimation , we are able to increase the attack success rate to over 90% if the attacker selectively attacks half of the users. Moreover, we show that our attack can correctly infer attributes for significantly more users than previous attacks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Birds of a Feather: Homophily in Social Networks
McPherson, M., Smith-Lovin, L., & Cook, J. M. (2001) · Annual Review of Sociology · doi:10.1146/annurev.soc.27.1.415 · Cited by 18,567
k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
SWEENEY, L. (2002) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488502001648 · Cited by 8,571 · cited 3×
“…an attacker can leverage the inferred attributes to link online users across multiple sites [2, 5, 19, 20] or with offline records (e.g., publicly available voter registration records) [45, 56] to form detailed and composite user profiles, which results in even bigger security and privacy risks.”
BackgroundAn efficient k-means clustering algorithm: analysis and implementation
Kanungo, T., Mount, D. M., Netanyahu, N. S., Piatko, C. D., Silverman, R., & Wu, A. Y. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1017616 · Cited by 5,660 · cited 1×
“, k-means [33]) to group the votes that our attack produces for all candidate attribute values into two clusters.”
BackgroundPrivate traits and attributes are predictable from digital records of human behavior
Kosinski, M., Stillwell, D., & Graepel, T. (2013) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1218772110 · Cited by 2,829
On the Feasibility of Internet-Scale Author Identification
Narayanan, A., Paskov, H., Gong, N. Z., Bethencourt, J., Stefanov, E., Shin, E. C. R., & Song, D. (2012) · 2012 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2012.46 · Cited by 261
Self-citationGaydar: Facebook Friendships Expose Sexual Orientation
Jernigan, C., & Mistree, B. F. T. (2009) · First Monday · doi:10.5210/fm.v14i10.2611 · Cited by 222
(2012) · doi:10.1145/2365952.2365989 · Cited by 170
(2017) · doi:10.1145/3038912.3052695 · Cited by 78
Self-citation
Cited by
Anonymization Techniques for Privacy Preserving Data Publishing: A Comprehensive Survey
Majeed, A., & Lee, S. (2021) · IEEE Access · doi:10.1109/access.2020.3045700 · Cited by 287
Comprehensive Privacy Analysis on Federated Recommender System Against Attribute Inference Attacks
Zhang, S., Yuan, W., & Yin, H. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3295601 · Cited by 97
Privacy-Aware Recommendation with Private-Attribute Protection using Adversarial Learning
Beigi, G., Mosallanezhad, A., Guo, R., Alvari, H., Nou, A., & Liu, H. (2020) · Proceedings of the 13th International Conference on Web Search and Data Mining · doi:10.1145/3336191.3371832 · Cited by 80
“ehavioral information such as movie-rating behavior [43] and Facebook likes [30] to infer their private attribute information. The third group of works exploits both friend and behavioral information [16, 17, 25]. Gong et al. [16, 17] make a social-behavior-attribute network in which all users’ behavioral and friendsh…”
Background(2017) · doi:10.1145/3038912.3052695 · Cited by 78
Self-citationSlokom, M., Hanjalic, A., & Larson, M. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102722 · Cited by 31
Metadata
- Authors
- Gong, N. Z., & Liu, B.
- Venue
- ACM Transactions on Privacy and Security
- Published
- 2018-01-02
- Volume
- 21
- Issue
- 1
- Pages
- 1-30
- ISSN
- 2471-2566 (ISSN-L)
- 2471-2574
- OpenAlex
- W2781896769
- Cited by
- 128
- References
- 9
- FWCI
- 7.50
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.