# Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification

arXiv: https://arxiv.org/abs/2408.01964 · HTML: https://mlsanity.com/paper/2408.01964/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 22 of its 61 references that are in the map.
- First posted on arXiv 4 Aug 2024.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 22 of 22)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [Adversarial Attack and Defense on Graph Data: A Survey](https://mlsanity.com/paper/1812.10528/) (2018)
- [Deep Reinforcement Learning in Large Discrete Action Spaces](https://mlsanity.com/paper/1512.07679/) (2015)
- [Representation Learning for Attributed Multiplex Heterogeneous Network](https://mlsanity.com/paper/1905.01669/) (2019)
- [Fast Gradient Attack on Network Embedding](https://mlsanity.com/paper/1809.02797/) (2018)
- [A Survey of Graph Neural Networks for Social Recommender Systems](https://mlsanity.com/paper/2212.04481/) (2022)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN](https://mlsanity.com/paper/2108.11883/) (2021)
- [HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding](https://mlsanity.com/paper/1909.03228/) (2019)
- [Efficient Heterogeneous Graph Learning via Random Projection](https://mlsanity.com/paper/2310.14481/) (2023)
- [Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Model](https://mlsanity.com/paper/2109.02058/) (2021)
- [Modeling Dynamic Heterogeneous Graph and Node Importance for Future Citation Prediction](https://mlsanity.com/paper/2305.17417/) (2023)
- [Simple and Efficient Partial Graph Adversarial Attack: A New Perspective](https://mlsanity.com/paper/2308.07834/) (2023)
- [HGAttack: Transferable Heterogeneous Graph Adversarial Attack](https://mlsanity.com/paper/2401.09945/) (2024)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have attracted substantial interest due to their exceptional performance on graph-based data. However, their robustness, especially on heterogeneous graphs, remains underexplored, particularly against adversarial attacks. This paper proposes HeteroKRLAttack, a targeted evasion black-box attack method for heterogeneous graphs. By integrating reinforcement learning with a Top-K algorithm to reduce the action space, our method efficiently identifies effective attack strategies to disrupt node classification tasks. We validate the effectiveness of HeteroKRLAttack through experiments on multiple heterogeneous graph datasets, showing significant reductions in classification accuracy compared to baseline methods. An ablation study underscores the critical role of the Top-K algorithm in enhancing attack performance. Our findings highlight potential vulnerabilities in current models and provide guidance for future defense strategies against adversarial attacks on heterogeneous graphs.