# Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection

arXiv: https://arxiv.org/abs/2602.00318 · HTML: https://mlsanity.com/paper/2602.00318/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 27 of 27)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Graph Random Neural Network for Semi-Supervised Learning on Graphs](https://mlsanity.com/paper/2005.11079/) (2020)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [A Gentle Introduction to Deep Learning for Graphs](https://mlsanity.com/paper/1912.12693/) (2019)
- [Robustness of Graph Neural Networks at Scale](https://mlsanity.com/paper/2110.14038/) (2021)
- [The Rise of Social Bots](https://mlsanity.com/paper/1407.5225/) (2014)
- [Fast Gradient Attack on Network Embedding](https://mlsanity.com/paper/1809.02797/) (2018)
- [Online Human-Bot Interactions: Detection, Estimation, and Characterization](https://mlsanity.com/paper/1703.03107/) (2017)
- [GOT: An Optimal Transport framework for Graph comparison](https://mlsanity.com/paper/1906.02085/) (2019)
- [TwiBot-20: A Comprehensive Twitter Bot Detection Benchmark](https://mlsanity.com/paper/2106.13088/) (2021)
- [TwiBot-22: Towards Graph-Based Twitter Bot Detection](https://mlsanity.com/paper/2206.04564/) (2022)
- [Heterogeneity-aware Twitter Bot Detection with Relational Graph Transformers](https://mlsanity.com/paper/2109.02927/) (2021)
- [BotRGCN: Twitter Bot Detection with Relational Graph Convolutional Networks](https://mlsanity.com/paper/2106.13092/) (2021)
- [Deep Neural Networks for Bot Detection](https://mlsanity.com/paper/1802.04289/) (2018)
- [Fame for sale: efficient detection of fake Twitter followers](https://mlsanity.com/paper/1509.04098/) (2015)
- [BotSim: LLM-Powered Malicious Social Botnet Simulation](https://mlsanity.com/paper/2412.13420/) (2024)
- [Pure Message Passing Can Estimate Common Neighbor for Link Prediction](https://mlsanity.com/paper/2309.00976/) (2023)
- [A Simple and Yet Fairly Effective Defense for Graph Neural Networks](https://mlsanity.com/paper/2402.13987/) (2024)
- [SCR: Training Graph Neural Networks with Consistency Regularization](https://mlsanity.com/paper/2112.04319/) (2021)
- [Better Safe Than Sorry: An Adversarial Approach to Improve Social Bot Detection](https://mlsanity.com/paper/1904.05132/) (2019)
- [Simple and Efficient Partial Graph Adversarial Attack: A New Perspective](https://mlsanity.com/paper/2308.07834/) (2023)
- [My Brother Helps Me: Node Injection Based Adversarial Attack on Social Bot Detection](https://mlsanity.com/paper/2310.07159/) (2023)
- [Z-REx: Human-Interpretable GNN Explanations for Real Estate Recommendations](https://mlsanity.com/paper/2503.18001/) (2025)

## Built on by (most cited first, 1 of 1)

- [Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments](https://mlsanity.com/paper/2602.19450/) (2026)

## Abstract (arXiv)

The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingly rely on Graph Neural Networks (GNNs). However, the effectiveness of these GNN-based detectors in real-world settings remains poorly understood. In practice, attackers continuously adapt their strategies as well as must operate under domain-specific and temporal constraints, which can fundamentally limit the applicability of existing attack methods. As a result, there is a critical need for robust GNN-based bot detection methods under realistic, constraint-aware attack scenarios. To address this gap, we introduce BOCLOAK to systematically evaluate the robustness of GNN-based social bot detection via both edge editing and node injection adversarial attacks under realistic constraints. BOCLOAK constructs a probability measure over spatio-temporal neighbor features and learns an optimal transport geometry that separates human and bot behaviors. It then decodes transport plans into sparse, plausible edge edits that evade detection while obeying real-world constraints. We evaluate BOCLOAK across three social bot datasets, five state-of-the-art bot detectors, three adversarial defenses, and compare it against four leading graph adversarial attack baselines. BOCLOAK achieves up to 80.13% higher attack success rates while using 99.80% less GPU memory under realistic real-world constraints. Most importantly, BOCLOAK shows that optimal transport provides a lightweight, principled framework for bridging the gap between adversarial attacks and real-world bot detection.