arXiv subjects

Rachel G. de Jong

Publications and source records attributed to Rachel G. de Jong.

5 recordsLinked to original sources

arXiv2026

Fuzzy k-anonymity in complex networks

With the introduction of large-scale network data, including population-scale social networks, techniques for privacy-aware sharing of network data become increasingly important. While existing $k$-anonymity approaches can model different attacker scenarios, they typically assume that attacker knowledge exactly matches the published network structure. We argue that exact knowledge is often unrealistic and introduce $ϕ$-$k$-anonymity, a fuzzy variant of $k$-anonymity in which parameter $ϕ$ captures the level of uncertainty in attacker knowledge. Across a benchmark of $39$ real-world networks, a realistic level of uncertainty ($ϕ=5\%$) renders, on average, $64\%$ of previously unique nodes anonymous. To further enhance anonymity, we apply anonymization algorithms under a $5\%$ edge modification budget. While full anonymization is often unattainable under exact $k$-anonymity, with low uncertainty ($ϕ=10\%$) our newly proposed Greedy algorithm anonymizes over $99\%$ of the nodes. Uncertainty also enables effective anonymization in otherwise difficult to anonymize dense synthetic graphs. Additionally, data utility in terms of structural properties and performance on network analysis tasks is well preserved, with most metrics changing less than $5\%$. Overall, our findings suggest that modest uncertainty assumptions yield high levels of anonymity and utility, motivating further research on uncertainty-aware privacy guarantees for network data.

cs.SI↗

arXiv2026

The anonymization problem in social networks

This paper introduces a unified computational framework for the anonymization problem in social networks, where the objective is to maximize node anonymity through graph alterations. We define three variants of the underlying optimization problem: full, partial and budgeted anonymization. In each variant, the objective is to maximize the number of $k$-anonymous nodes, i.e., nodes for which at least $k-1$ other nodes are equivalent under a particular anonymity measure. We propose four new heuristic network anonymization algorithms and implement these in ANO-NET, a reusable computational framework. Experiments on three common graph models and 19 real-world network datasets yield three empirical findings. First, regarding the method of alteration, experiments on graph models show that random edge deletion is more effective than edge rewiring and addition. Second, we show that the choice of anonymity measure strongly affects both initial network anonymity and the difficulty of anonymization. This highlights the importance of careful measure selection, matching a realistic attacker scenario. Third, comparing the four proposed algorithms and an edge sampling baseline from the literature, we find that an approach which preferentially deletes edges affecting structurally unique nodes, consistently outperforms heuristics based solely on network structure. Overall, our best performing algorithm retains on average 14 times more edges in full anonymization. Moreover, it yields 4.8 times more anonymous nodes than the baseline in the budgeted variant. On top of that, the best performing algorithm achieves a better trade-off between anonymity and data utility. This work provides a foundation for the future development of effective network anonymization algorithms.

cs.SI↗

arXiv2025

A systematic comparison of measures for publishing k-anonymous social network data

Sharing or publishing social network data while accounting for privacy of individuals is a difficult task due to the interconnectedness of nodes in networks. A key question in k-anonymity, a widely studied notion of privacy, is how to measure the anonymity of an individual, as this determines the attacker scenarios one protects against. In this paper, we systematically compare the most prominent anonymity measures from the literature in terms of the completeness and reach of the structural information they take into account. We present a theoretical characterization and a distance-parametrized strictness ordering of the existing measures for k-anonymity in networks. In addition, we conduct empirical experiments on a wide range of real-world network datasets with up to millions of edges. Our findings reveal that the choice of the measure significantly impacts the measured level of anonymity and hence the effectiveness of the corresponding attacker scenario, the privacy vs. utility trade-off, and computational cost. Surprisingly, we find that the anonymity measure representing the most effective attacker scenario considers a greater node vicinity yet utilizes only limited structural information and therewith minimal computational resources. Overall, the insights provided in this work offer researchers and practitioners practical guidance for selecting appropriate anonymity measures when sharing or publishing social network data under privacy constraints.

cs.SI↗

arXiv2025

Utility-aware Social Network Anonymization using Genetic Algorithms

Social networks may contain privacy-sensitive information about individuals. The objective of the network anonymization problem is to alter a given social network dataset such that the number of anonymous nodes in the social graph is maximized. Here, a node is anonymous if it does not have a unique surrounding network structure. At the same time, the aim is to ensure data utility, i.e., preserve topological network properties and retain good performance on downstream network analysis tasks. We propose two versions of a genetic algorithm tailored to this problem: one generic GA and a uniqueness-aware GA (UGA). The latter aims to target edges more effectively during mutation by avoiding edges connected to already anonymous nodes. After hyperparameter tuning, we compare the two GAs against two existing baseline algorithms on several real-world network datasets. Results show that the proposed genetic algorithms manage to anonymize on average 14 times more nodes than the best baseline algorithm. Additionally, data utility experiments demonstrate how the UGA requires fewer edge deletions, and how our GAs and the baselines retain performance on downstream tasks equally well. Overall, our results suggest that genetic algorithms are a promising approach for finding solutions to the network anonymization problem.

cs.SI↗

arXiv2023

The effect of distant connections on node anonymity in complex networks

Ensuring privacy of individuals is of paramount importance to social network analysis research. Previous work assessed anonymity in a network based on the non-uniqueness of a node's ego network. In this work, we show that this approach does not adequately account for the strong de-anonymizing effect of distant connections. We first propose the use of d-k-anonymity, a novel measure that takes knowledge up to distance d of a considered node into account. Second, we introduce anonymity-cascade, which exploits the so-called infectiousness of uniqueness: mere information about being connected to another unique node can make a given node uniquely identifiable. These two approaches, together with relevant "twin node" processing steps in the underlying graph structure, offer practitioners flexible solutions, tunable in precision and computation time. This enables the assessment of anonymity in large-scale networks with up to millions of nodes and edges. Experiments on graph models and a wide range of real-world networks show drastic decreases in anonymity when connections at distance 2 are considered. Moreover, extending the knowledge beyond the ego network with just one extra link often already decreases overall anonymity by over 50%. These findings have important implications for privacy-aware sharing of sensitive network data.

cs.SI↗