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

TL;DR

This paper demonstrates how adversarial socialbots can be modeled using multi-agent hierarchical reinforcement learning to maximize influence while avoiding detection, revealing vulnerabilities in current social platform defenses.

Contribution

The paper introduces a novel hierarchical RL framework modeling adversarial socialbots, showing they can effectively evade detection and influence networks in realistic scenarios.

Findings

Adversarial socialbots can increase influence by up to 18%.

Stealthiness of socialbots can be improved by up to 40%.

The approach scales linearly and is practical for real-world deployment.

Abstract

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.