# Leveraging Vulnerabilities in Temporal Graph Neural Networks via Strategic High-Impact Assaults

arXiv: https://arxiv.org/abs/2509.25418 · HTML: https://mlsanity.com/paper/2509.25418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective](https://mlsanity.com/paper/1906.04214/) (2019)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Adversarial Attack and Defense on Graph Data: A Survey](https://mlsanity.com/paper/1812.10528/) (2018)
- [Towards More Practical Adversarial Attacks on Graph Neural Networks](https://mlsanity.com/paper/2006.05057/) (2020)
- [TDGIA:Effective Injection Attacks on Graph Neural Networks](https://mlsanity.com/paper/2106.06663/) (2021)
- [Fast Gradient Attack on Network Embedding](https://mlsanity.com/paper/1809.02797/) (2018)
- [Adversarial Attack on Large Scale Graph](https://mlsanity.com/paper/2009.03488/) (2020)
- [Adversarial Attacks on Deep Models for Financial Transaction Records](https://mlsanity.com/paper/2106.08361/) (2021)
- [Reinforcement learning on graphs: A survey](https://mlsanity.com/paper/2204.06127/) (2022)
- [RelExt: Relation Extraction using Deep Learning approaches for Cybersecurity Knowledge Graph Improvement](https://mlsanity.com/paper/1905.02497/) (2019)
- [Time-aware Gradient Attack on Dynamic Network Link Prediction](https://mlsanity.com/paper/1911.10561/) (2019)
- [Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2308.10779/) (2023)
- [Centrality Measures in Complex Networks: A Survey](https://mlsanity.com/paper/2011.07190/) (2020)
- [Structack: Structure-based Adversarial Attacks on Graph Neural Networks](https://mlsanity.com/paper/2107.11327/) (2021)
- [HGAttack: Transferable Heterogeneous Graph Adversarial Attack](https://mlsanity.com/paper/2401.09945/) (2024)
- [KGIF: Optimizing Relation-Aware Recommendations with Knowledge Graph Information Fusion](https://mlsanity.com/paper/2501.04161/) (2025)

## Abstract (arXiv)

Temporal Graph Neural Networks (TGNNs) have become indispensable for analyzing dynamic graphs in critical applications such as social networks, communication systems, and financial networks. However, the robustness of TGNNs against adversarial attacks, particularly sophisticated attacks that exploit the temporal dimension, remains a significant challenge. Existing attack methods for Spatio-Temporal Dynamic Graphs (STDGs) often rely on simplistic, easily detectable perturbations (e.g., random edge additions/deletions) and fail to strategically target the most influential nodes and edges for maximum impact. We introduce the High Impact Attack (HIA), a novel restricted black-box attack framework specifically designed to overcome these limitations and expose critical vulnerabilities in TGNNs. HIA leverages a data-driven surrogate model to identify structurally important nodes (central to network connectivity) and dynamically important nodes (critical for the graph's temporal evolution). It then employs a hybrid perturbation strategy, combining strategic edge injection (to create misleading connections) and targeted edge deletion (to disrupt essential pathways), maximizing TGNN performance degradation. Importantly, HIA minimizes the number of perturbations to enhance stealth, making it more challenging to detect. Comprehensive experiments on five real-world datasets and four representative TGNN architectures (TGN, JODIE, DySAT, and TGAT) demonstrate that HIA significantly reduces TGNN accuracy on the link prediction task, achieving up to a 35.55% decrease in Mean Reciprocal Rank (MRR) - a substantial improvement over state-of-the-art baselines. These results highlight fundamental vulnerabilities in current STDG models and underscore the urgent need for robust defenses that account for both structural and temporal dynamics.