# Adversarial Robustness of Link Sign Prediction in Signed Graphs

arXiv: https://arxiv.org/abs/2401.10590 · HTML: https://mlsanity.com/paper/2401.10590/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 79 references that are in the map.
- First posted on arXiv 19 Jan 2024.

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

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Adversarial Attacks on Graph Neural Networks via Meta Learning](https://mlsanity.com/paper/1902.08412/) (2019)
- [Adversarial Graph Augmentation to Improve Graph Contrastive Learning](https://mlsanity.com/paper/2106.05819/) (2021)
- [Adversarial Attack and Defense on Graph Data: A Survey](https://mlsanity.com/paper/1812.10528/) (2018)
- [Adversarial Attacks on Node Embeddings via Graph Poisoning](https://mlsanity.com/paper/1809.01093/) (2018)
- [InfoGCL: Information-Aware Graph Contrastive Learning](https://mlsanity.com/paper/2110.15438/) (2021)
- [Graph Barlow Twins: A self-supervised representation learning framework for graphs](https://mlsanity.com/paper/2106.02466/) (2021)
- [GSLB: The Graph Structure Learning Benchmark](https://mlsanity.com/paper/2310.05174/) (2023)
- [SDGNN: Learning Node Representation for Signed Directed Networks](https://mlsanity.com/paper/2101.02390/) (2021)
- [A Survey of Signed Network Mining in Social Media](https://mlsanity.com/paper/1511.07569/) (2015)
- [Where are we in embedding spaces? A Comprehensive Analysis on Network Embedding Approaches for Recommender Systems](https://mlsanity.com/paper/2105.08908/) (2021)
- [Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach](https://mlsanity.com/paper/2310.06396/) (2023)
- [POLE: Polarized Embedding for Signed Networks](https://mlsanity.com/paper/2110.09899/) (2021)
- [A Robust and Generalized Framework for Adversarial Graph Embedding](https://mlsanity.com/paper/2105.10651/) (2021)
- [wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction](https://mlsanity.com/paper/2109.11519/) (2021)
- [FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification](https://mlsanity.com/paper/2210.13815/) (2022)
- [Adversarially Robust Neural Architecture Search for Graph Neural Networks](https://mlsanity.com/paper/2304.04168/) (2023)
- [Balance in signed networks](https://mlsanity.com/paper/1809.05140/) (2018)
- [Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach](https://mlsanity.com/paper/2308.01063/) (2023)
- [Black-Box Attacks against Signed Graph Analysis via Balance Poisoning](https://mlsanity.com/paper/2309.02396/) (2023)
- [Cost Aware Untargeted Poisoning Attack against Graph Neural Networks,](https://mlsanity.com/paper/2312.07158/) (2023)

## Abstract (arXiv)

Signed graphs serve as fundamental data structures for representing positive and negative relationships in social networks, with signed graph neural networks (SGNNs) emerging as the primary tool for their analysis. Our investigation reveals that balance theory, while essential for modeling signed relationships in SGNNs, inadvertently introduces exploitable vulnerabilities to black-box attacks. To showcase this, we propose balance-attack, a novel adversarial strategy specifically designed to compromise graph balance degree, and develop an efficient heuristic algorithm to solve the associated NP-hard optimization problem. While existing approaches attempt to restore attacked graphs through balance learning techniques, they face a critical challenge we term "Irreversibility of Balance-related Information," as restored edges fail to align with original attack targets. To address this limitation, we introduce Balance Augmented-Signed Graph Contrastive Learning (BA-SGCL), an innovative framework that combines contrastive learning with balance augmentation techniques to achieve robust graph representations. By maintaining high balance degree in the latent space, BA-SGCL not only effectively circumvents the irreversibility challenge but also significantly enhances model resilience. Extensive experiments across multiple SGNN architectures and real-world datasets demonstrate both the effectiveness of our proposed balance-attack and the superior robustness of BA-SGCL, advancing the security and reliability of signed graph analysis in social networks. Datasets and codes of the proposed framework are at the github repository https://anonymous.4open.science/r/BA-SGCL-submit-DF41/.