Data Poisoning Attacks to Local Differential Privacy Protocols for Graphs

• URL: http://arxiv.org/abs/2412.19837v1
• Date: Mon, 23 Dec 2024 11:16:23 GMT
• Title: Data Poisoning Attacks to Local Differential Privacy Protocols for Graphs
• Authors: Xi He, Kai Huang, Qingqing Ye, Haibo Hu,
• Abstract summary: This paper shows that an attacker can inject fake users into Local Differential Privacy protocols for graphs and design data poisoning attacks to degrade the quality of graph metrics.<n>As a proof of concept, we focus on data poisoning attacks on two classical graph metrics: degree centrality and clustering coefficient.<n> Experimental study on real-world datasets demonstrates that our attacks can largely degrade the quality of collected graph metrics datasets.
• Score: 12.565077847109974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph analysis has become increasingly popular with the prevalence of big data and machine learning. Traditional graph data analysis methods often assume the existence of a trusted third party to collect and store the graph data, which does not align with real-world situations. To address this, some research has proposed utilizing Local Differential Privacy (LDP) to collect graph data or graph metrics (e.g., clustering coefficient). This line of research focuses on collecting two atomic graph metrics (the adjacency bit vectors and node degrees) from each node locally under LDP to synthesize an entire graph or generate graph metrics. However, they have not considered the security issues of LDP for graphs. In this paper, we bridge the gap by demonstrating that an attacker can inject fake users into LDP protocols for graphs and design data poisoning attacks to degrade the quality of graph metrics. In particular, we present three data poisoning attacks to LDP protocols for graphs. As a proof of concept, we focus on data poisoning attacks on two classical graph metrics: degree centrality and clustering coefficient. We further design two countermeasures for these data poisoning attacks. Experimental study on real-world datasets demonstrates that our attacks can largely degrade the quality of collected graph metrics, and the proposed countermeasures cannot effectively offset the effect, which calls for the development of new defenses.

Related papers

• Cluster-Aware Attacks on Graph Watermarks [50.19105800063768]
  We introduce a cluster-aware threat model in which adversaries apply community-guided modifications to evade detection. Our results show that cluster-aware attacks can reduce attribution accuracy by up to 80% more than random baselines. We propose a lightweight embedding enhancement that distributes watermark nodes across graph communities.
  arXiv  Detail & Related papers  (2025-04-24T22:49:28Z)
• DPGAN: A Dual-Path Generative Adversarial Network for Missing Data Imputation in Graphs [17.847551850315895]
  This paper proposes a novel framework, called Dual-Pathrative Adversarial Network (DPGAN) DPGAN can deal simultaneously with missing data and avoid over-smoothing problems. Comprehensive experiments across various benchmark datasets substantiate that DPGAN consistently rivals, if not outperforms, existing state-of-the-art imputation algorithms.
  arXiv  Detail & Related papers  (2024-04-26T05:26:10Z)
• GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networks [69.97213941893351]
  The emergence of Graph Neural Networks (GNNs) in graph data analysis has raised critical concerns about data misuse during model training. Existing methodologies address either data misuse detection or mitigation, and are primarily designed for local GNN models. This paper introduces a pioneering approach called GraphGuard, to tackle these challenges.
  arXiv  Detail & Related papers  (2023-12-13T02:59:37Z)
• Crypto'Graph: Leveraging Privacy-Preserving Distributed Link Prediction for Robust Graph Learning [2.048226951354646]
  Crypto'Graph is an efficient protocol for privacy-preserving link prediction on distributed graphs. It is illustrated for defense against graph poisoning attacks, in which it is possible to identify potential adversarial links without compromising the privacy of the graphs of individual parties.
  arXiv  Detail & Related papers  (2023-09-19T19:30:28Z)
• EDoG: Adversarial Edge Detection For Graph Neural Networks [17.969573886307906]
  Graph Neural Networks (GNNs) have been widely applied to different tasks such as bioinformatics, drug design, and social networks. Recent studies have shown that GNNs are vulnerable to adversarial attacks which aim to mislead the node or subgraph classification prediction by adding subtle perturbations. We propose a general adversarial edge detection pipeline EDoG without requiring knowledge of the attack strategies based on graph generation.
  arXiv  Detail & Related papers  (2022-12-27T20:42:36Z)
• Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation [60.50994154879244]
  Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack. We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
  arXiv  Detail & Related papers  (2022-11-15T11:44:31Z)
• Robustness of Locally Differentially Private Graph Analysis Against Poisoning [34.86995628705397]
  Locally differentially private (LDP) graph analysis allows private analysis on a graph that is distributed across multiple users.<n>We study the impact of poisoning attacks for graph degree estimation protocols under LDP.<n>We design robust degree estimation protocols under LDP that can significantly reduce the impact of data poisoning and compute degree estimates with high accuracy.
  arXiv  Detail & Related papers  (2022-10-25T22:55:08Z)
• Privacy-Preserved Neural Graph Similarity Learning [99.78599103903777]
  We propose a novel Privacy-Preserving neural Graph Matching network model, named PPGM, for graph similarity learning. To prevent reconstruction attacks, the proposed model does not communicate node-level representations between devices. To alleviate the attacks to graph properties, the obfuscated features that contain information from both vectors are communicated.
  arXiv  Detail & Related papers  (2022-10-21T04:38:25Z)
• Model Inversion Attacks against Graph Neural Networks [65.35955643325038]
  We study model inversion attacks against Graph Neural Networks (GNNs) In this paper, we present GraphMI to infer the private training graph data. Our experimental results show that such defenses are not sufficiently effective and call for more advanced defenses against privacy attacks.
  arXiv  Detail & Related papers  (2022-09-16T09:13:43Z)
• Inference Attacks Against Graph Neural Networks [33.19531086886817]
  Graph embedding is a powerful tool to solve the graph analytics problem. While sharing graph embedding is intriguing, the associated privacy risks are unexplored. We systematically investigate the information leakage of the graph embedding by mounting three inference attacks.
  arXiv  Detail & Related papers  (2021-10-06T10:08:11Z)
• GraphMI: Extracting Private Graph Data from Graph Neural Networks [59.05178231559796]
  We present textbfGraph textbfModel textbfInversion attack (GraphMI), which aims to extract private graph data of the training graph by inverting GNN. Specifically, we propose a projected gradient module to tackle the discreteness of graph edges while preserving the sparsity and smoothness of graph features. We design a graph auto-encoder module to efficiently exploit graph topology, node attributes, and target model parameters for edge inference.
  arXiv  Detail & Related papers  (2021-06-05T07:07:52Z)
• Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs [87.5882042724041]
  Link prediction in dynamic graphs (LPDG) is an important research problem that has diverse applications. We study the vulnerability of LPDG methods and propose the first practical black-box evasion attack.
  arXiv  Detail & Related papers  (2020-09-01T01:04:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.