Reinforcement-Learning Based Covert Social Influence Operations

Saurabh Kumar, Valerio La Gatta, Andrea Pugliese, Andrew Pulver, VS Subrahmanian, Jiazhi Zhang, Youzhi Zhang

Track: Social networks and social media

Keywords: Influence Operations; Human-Bot Interaction; Social Media; Human Subject Study

TL;DR: This paper presents a reinforcement learning framework using a Markov Decision Process to model Covert Social Influence Operations (CSIOs) on social media, optimizing the actions of CSIO agents to manipulate public opinion while evading detection.

Abstract: How might reinforcement-learning based covert social influence operations (CSIOs) be run, given that the CSIO agent wants to maximize influence and minimize discoverability of malicious accounts? And how successful can they be, given that both social platform bot detectors and humans might report them to the social platform? To answer these questions, we propose RL_CSIO, an RL-based methodology for running CSIOs and run 4 CSIOs with IRB-approval over a period of 5 days using a panel of 225 human subjects. We explore 8 research questions based on the data collected. The results show that RL_CSIO agents successfully trade off influence and discoverability - but in ways that are nuanced and unexpected.

Submission Number: 2333