# Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning

arXiv: https://arxiv.org/abs/2110.10655 · HTML: https://mlsanity.com/paper/2110.10655/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 56 references that are in the map.
- First posted on arXiv 20 Oct 2021.

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [A Convolutional Neural Network for Modelling Sentences](https://mlsanity.com/paper/1404.2188/) (2014)
- [Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning](https://mlsanity.com/paper/2010.12367/) (2020)
- [Stochastic Neural Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1704.03012/) (2017)
- [The spread of low-credibility content by social bots](https://mlsanity.com/paper/1707.07592/) (2017)
- [Autonomous Drone Racing with Deep Reinforcement Learning](https://mlsanity.com/paper/2103.08624/) (2021)
- [Scalable and Generalizable Social Bot Detection through Data Selection](https://mlsanity.com/paper/1911.09179/) (2019)
- [The paradigm-shift of social spambots: Evidence, theories, and tools for the arms race](https://mlsanity.com/paper/1701.03017/) (2017)
- [Horizon: Facebook's Open Source Applied Reinforcement Learning Platform](https://mlsanity.com/paper/1811.00260/) (2018)
- [A Decade of Social Bot Detection](https://mlsanity.com/paper/2007.03604/) (2020)
- [BotOrNot: A System to Evaluate Social Bots](https://mlsanity.com/paper/1602.00975/) (2016)
- [Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards](https://mlsanity.com/paper/1910.04450/) (2019)
- [Influence Maximization: Near-Optimal Time Complexity Meets Practical Efficiency](https://mlsanity.com/paper/1404.0900/) (2014)
- [Detection of Novel Social Bots by Ensembles of Specialized Classifiers](https://mlsanity.com/paper/2006.06867/) (2020)
- [RTbust: Exploiting Temporal Patterns for Botnet Detection on Twitter](https://mlsanity.com/paper/1902.04506/) (2019)
- [MALCOM: Generating Malicious Comments to Attack Neural Fake News Detection Models](https://mlsanity.com/paper/2009.01048/) (2020)
- [Arming the public with artificial intelligence to counter social bots](https://mlsanity.com/paper/1901.00912/) (2019)
- [Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling](https://mlsanity.com/paper/1907.11625/) (2019)
- [The DARPA Twitter Bot Challenge](https://mlsanity.com/paper/1601.05140/) (2016)
- [TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search](https://mlsanity.com/paper/2006.07078/) (2020)
- [DISCO: Influence Maximization Meets Network Embedding and Deep Learning](https://mlsanity.com/paper/1906.07378/) (2019)
- [Better Safe Than Sorry: An Adversarial Approach to Improve Social Bot Detection](https://mlsanity.com/paper/1904.05132/) (2019)
- [CLAIM: Curriculum Learning Policy for Influence Maximization in Unknown Social Networks](https://mlsanity.com/paper/2107.03603/) (2021)
- [Two Evidential Data Based Models for Influence Maximization in Twitter](https://mlsanity.com/paper/1701.05751/) (2017)

## Built on by (most cited first, 3 of 3)

- [False Information, Bots and Malicious Campaigns: Demystifying Elements of Social Media Manipulations](https://mlsanity.com/paper/2308.12497/) (2023)
- [RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction](https://mlsanity.com/paper/2510.16035/) (2025)
- [Model-Free Learning and Optimal Policy Design in Multi-Agent MDPs Under Probabilistic Agent Dropout](https://mlsanity.com/paper/2304.12458/) (2023)

## Abstract (arXiv)

Socialbots are software-driven user accounts on social platforms, acting autonomously (mimicking human behavior), with the aims to influence the opinions of other users or spread targeted misinformation for particular goals. As socialbots undermine the ecosystem of social platforms, they are often considered harmful. As such, there have been several computational efforts to auto-detect the socialbots. However, to our best knowledge, the adversarial nature of these socialbots has not yet been studied. This begs a question "can adversaries, controlling socialbots, exploit AI techniques to their advantage?" To this question, we successfully demonstrate that indeed it is possible for adversaries to exploit computational learning mechanism such as reinforcement learning (RL) to maximize the influence of socialbots while avoiding being detected. We first formulate the adversarial socialbot learning as a cooperative game between two functional hierarchical RL agents. While one agent curates a sequence of activities that can avoid the detection, the other agent aims to maximize network influence by selectively connecting with right users. Our proposed policy networks train with a vast amount of synthetic graphs and generalize better than baselines on unseen real-life graphs both in terms of maximizing network influence (up to +18%) and sustainable stealthiness (up to +40% undetectability) under a strong bot detector (with 90% detection accuracy). During inference, the complexity of our approach scales linearly, independent of a network's structure and the virality of news. This makes our approach a practical adversarial attack when deployed in a real-life setting.