Graph Data Anonymization, De-Anonymization Attacks, and De-Anonymizability Quantification: A Survey
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Nowadays, many computer and communication systems generate graph data. Graph data span many different domains, ranging from online social network data from networks like Facebook to epidemiological data used to study the spread of infectious diseases. Graph data are shared regularly for many purposes including academic research and for business collaborations. Since graph data may be sensitive, data owners often use various anonymization techniques that often compromise the resulting utility of the anonymized data. To make matters worse, there are several state-of-the-art graph data de-anonymization attacks that have proven successful in recent years. In this paper, we survey the graph data anonymization, de-anonymization, and de-anonymizability quantification techniques in the past decade. Specifically, we systematically classify, summarize, and analyze state-of-the-art graph data anonymization, de-anonymization, and de-anonymizability quantification techniques. For existing graph data anonymization techniques, we classify them into six categories and analyze their utility performance with respect to 15 fundamental graph utility metrics and seven high-level application utility metrics. For existing de-anonymization attacks, we classify them into two categories and examine their performance with respect to scalability, practicability, robustness, etc. We also analyze the resistance of existing graph anonymization techniques against existing graph de-anonymizaiton attacks. For existing de-anonymizability quantifications, we classify them according to whether they consider seed information or not, and analyze them in terms of their soundness. Our analysis demonstrates that: 1) most anonymization schemes can partially or conditionally preserve most graph utility while losing some application utility and 2) state-of-the-art anonymization schemes are vulnerable to several or all of the emerging structure-based de-anonymization attacks. The actual vulnerability of each anonymization algorithm depends on how much and which data utility it preserves. Based on our summarization and analysis, we discuss the research evolution, future directions, and challenges in the research area of graph data anonymization, de-anonymization, and de-anonymizability quantification.
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
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 1×
“defined by Samarati and Sweeney [108], [109], opened a prosperous research area of data anonymization.”
BackgroundError and attack tolerance of complex networks
Albert, R., Jeong, H., & Barabási, A.-L. (2000) · Nature · doi:10.1038/35019019 · Cited by 7,534
Newman, M. (2010) · doi:10.1093/acprof:oso/9780199206650.001.0001 · Cited by 6,595
L -diversity: Privacy beyond k -anonymity
Machanavajjhala, A., Kifer, D., Gehrke, J., & Venkitasubramaniam, M. (2007) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/1217299.1217302 · Cited by 3,617 · cited 3×
“proposed l-diversity in [110], under which each equivalence class has at least l well-represented values for each sensitive attribute.”
BackgroundInfluentialt-Closeness: Privacy Beyond k-Anonymity and l-Diversity
Li, N., Li, T., & Venkatasubramanian, S. (2007) · 2007 IEEE 23rd International Conference on Data Engineering · doi:10.1109/icde.2007.367856 · Cited by 3,451 · cited 2×
“[111] proposed t-closeness, which requires that the distribution of a sensitive attribute in any equivalence class should be close to the attribute distribution in the overall dataset.”
BackgroundMeasurement and analysis of online social networks
Mislove, A., Marcon, M., Gummadi, K. P., Druschel, P., & Bhattacharjee, B. (2007) · Proceedings of the 7th ACM SIGCOMM conference on Internet measurement · doi:10.1145/1298306.1298311 · Cited by 3,057
Robust De-anonymization of Large Sparse Datasets
Narayanan, A., & Shmatikov, V. (2008) · 2008 IEEE Symposium on Security and Privacy (sp 2008) · doi:10.1109/sp.2008.33 · Cited by 2,372 · cited 15×
“[10]–[13] Cluster [15], [17] DP [18]–[22] RW [23] Backstrom et al. [74] Narayanan-Shmatikov [1] Narayanan et al. [75] Nilizadeh et al. [2] Srivatsa-Hicks [3] Pedarsani et al. [29] Yartseva and Grossglauser [25] Ji et al. [26] Korula-Lattanzi [28] Ji et al. [4] state-of-the-art anonymization schemes in Table IV, where…”
BackgroundInfluentialGraphs over time: densification laws, shrinking diameters and possible explanations
Leskovec, J., Kleinberg, J., & Faloutsos, C. (2005) · Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining · doi:10.1145/1081870.1081893 · Cited by 2,281
Our Data, Ourselves: Privacy Via Distributed Noise Generation
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., & Naor, M. (2006) · Lecture Notes in Computer Science · doi:10.1007/11761679_29 · Cited by 1,835 · cited 1×
“[133], [134], is another popular anonymization technique to provide a provable strong privacy guarantee.”
BackgroundPrivacy-preserving data publishing: A survey of recent developments
Fung, B. C. M., Wang, K., Chen, R., & Yu, P. S. (2010) · ACM Computing Surveys · doi:10.1145/1749603.1749605 · Cited by 1,704 · cited 1×
“[177] made a comprehensive survey on privacy preserving data publishing techniques for relational data,”
Background
Cited by
Trustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612
“For example, Reference [176] introduces several approaches into de-anonymize user information from graph data.”
Hassan, M. U., Rehmani, M. H., & Chen, J. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.02.060 · Cited by 520
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
Ali, M., Karimipour, H., & Tariq, M. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102355 · Cited by 177
A Review of Anonymization for Healthcare Data
Olatunji, I. E., Rauch, J., Katzensteiner, M., & Khosla, M. (2024) · Big Data · doi:10.1089/big.2021.0169 · Cited by 101
Trusted AI in Multiagent Systems: An Overview of Privacy and Security for Distributed Learning
Ma, C., Li, J., Wei, K., Liu, B., Ding, M., Yuan, L., Han, Z., & Vincent Poor, H. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3306773 · Cited by 96
Metadata
- Authors
- Ji, S., Mittal, P., & Beyah, R.
- Venue
- IEEE Communications Surveys & Tutorials
- Published
- 2017
- Volume
- 19
- Issue
- 2
- Pages
- 1305-1326
- ISSN
- 1553-877X (ISSN-L)
- OpenAlex
- W2558896083
- Cited by
- 141
- References
- 11
- FWCI
- 9.96
- 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.