# TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support

arXiv: https://arxiv.org/abs/2306.13339 · HTML: https://mlsanity.com/paper/2306.13339/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 87 references that are in the map.
- First posted on arXiv 23 Jun 2023.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Structured Sequence Modeling with Graph Convolutional Recurrent Networks](https://mlsanity.com/paper/1612.07659/) (2016)
- [A Comprehensive Survey on Graph Anomaly Detection with Deep Learning](https://mlsanity.com/paper/2106.07178/) (2021)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Graph Embedding Techniques, Applications, and Performance: A Survey](https://mlsanity.com/paper/1705.02801/) (2017)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Variational Graph Recurrent Neural Networks](https://mlsanity.com/paper/1908.09710/) (2019)
- [Subpopulation Data Poisoning Attacks](https://mlsanity.com/paper/2006.14026/) (2020)
- [LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis](https://mlsanity.com/paper/2108.06504/) (2021)
- [On the training dynamics of deep networks with L2 regularization](https://mlsanity.com/paper/2006.08643/) (2020)
- [ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation](https://mlsanity.com/paper/2105.02254/) (2021)
- [A comparison of deep networks with ReLU activation function and linear spline-type methods](https://mlsanity.com/paper/1804.02253/) (2018)
- [Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation](https://mlsanity.com/paper/1812.01661/) (2018)
- [Time-aware Gradient Attack on Dynamic Network Link Prediction](https://mlsanity.com/paper/1911.10561/) (2019)
- [TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Nature](https://mlsanity.com/paper/2205.12784/) (2022)
- [KGTrust: Evaluating Trustworthiness of SIoT via Knowledge Enhanced Graph Neural Networks](https://mlsanity.com/paper/2302.11396/) (2023)

## Built on by (most cited first, 12 of 12)

- [A Survey of Graph Unlearning](https://mlsanity.com/paper/2310.02164/) (2023)
- [Safety in Graph Machine Learning: Threats and Safeguards](https://mlsanity.com/paper/2405.11034/) (2024)
- [CAT: Can Trust be Predicted with Context-Awareness in Dynamic Heterogeneous Networks?](https://mlsanity.com/paper/2512.11352/) (2025)
- [Understanding the Robustness of Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2406.13920/) (2024)
- [GRExplainer: A Universal Explanation Method for Temporal Graph Neural Networks](https://mlsanity.com/paper/2512.22772/) (2025)
- [Enhancing Trust Management System for Connected Autonomous Vehicles Using Machine Learning Methods: A Survey](https://mlsanity.com/paper/2505.07882/) (2025)
- [DGTEN: A Robust Deep Gaussian based Graph Neural Network for Dynamic Trust Evaluation with Uncertainty-Quantification Support](https://mlsanity.com/paper/2510.07620/) (2025)
- [Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks](https://mlsanity.com/paper/2603.05004/) (2026)
- [A Survey on Quantitative Modeling of Trust in Online Social Networks](https://mlsanity.com/paper/2603.11054/) (2026)
- [TCHG: Tri-Trust Conditioned Heterogeneous Graph Learning for Reliable Dynamic Trust Prediction](https://mlsanity.com/paper/2606.16611/) (2026)
- [Long-Term Behavioral Evaluation for Trusted Collaborator Selection via Bidirectional Mamba](https://mlsanity.com/paper/2608.25232/) (2026)
- [LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation](https://mlsanity.com/paper/2609.33521/) (2026)

## Abstract (arXiv)

Trust evaluation assesses trust relationships between entities and facilitates decision-making. Machine Learning (ML) shows great potential for trust evaluation owing to its learning capabilities. In recent years, Graph Neural Networks (GNNs), as a new ML paradigm, have demonstrated superiority in dealing with graph data. This has motivated researchers to explore their use in trust evaluation, as trust relationships among entities can be modeled as a graph. However, current trust evaluation methods that employ GNNs fail to fully satisfy the dynamic nature of trust, overlook the adverse effects of trust-related attacks, and cannot provide convincing explanations on evaluation results. To address these problems, we propose TrustGuard, a GNN-based accurate trust evaluation model that supports trust dynamicity, is robust against typical attacks, and provides explanations through visualization. Specifically, TrustGuard is designed with a layered architecture that contains a snapshot input layer, a spatial aggregation layer, a temporal aggregation layer, and a prediction layer. Among them, the spatial aggregation layer adopts a defense mechanism to robustly aggregate local trust, and the temporal aggregation layer applies an attention mechanism for effective learning of temporal patterns. Extensive experiments on two real-world datasets show that TrustGuard outperforms state-of-the-art GNN-based trust evaluation models with respect to trust prediction across single-timeslot and multi-timeslot, even in the presence of attacks. In addition, TrustGuard can explain its evaluation results by visualizing both spatial and temporal views.