Adversarial Botometer: Adversarial Analysis for Social Bot Detection

TL;DR

This paper introduces an adversarial analysis framework for social bot detection, modeling interactions as a synthetic game, evaluating robustness against attacks, and analyzing dataset impacts to improve detection methods.

Contribution

It presents a novel adversarial evaluation approach for social bot detection, including a synthetic game model and cross-domain analysis to assess robustness and dataset effects.

Findings

Bot detection performance varies under adversarial attacks

Synthetic adversarial game reveals strengths and weaknesses of detection models

Cross-domain analysis highlights dataset influence on detection accuracy

Abstract

Social bots play a significant role in many online social networks (OSN) as they imitate human behavior. This fact raises difficult questions about their capabilities and potential risks. Given the recent advances in Generative AI (GenAI), social bots are capable of producing highly realistic and complex content that mimics human creativity. As the malicious social bots emerge to deceive people with their unrealistic content, identifying them and distinguishing the content they produce has become an actual challenge for numerous social platforms. Several approaches to this problem have already been proposed in the literature, but the proposed solutions have not been widely evaluated. To address this issue, we evaluate the behavior of a text-based bot detector in a competitive environment where some scenarios are proposed: \textit{First}, the tug-of-war between a bot and a bot detector is examined. It is interesting to analyze which party is more likely to prevail and which circumstances influence these expectations. In this regard, we model the problem as a synthetic adversarial game in which a conversational bot and a bot detector are engaged in strategic online interactions. \textit{Second}, the bot detection model is evaluated under attack examples generated by a social bot; to this end, we poison the dataset with attack examples and evaluate the model performance under this condition. \textit{Finally}, to investigate the impact of the dataset, a cross-domain analysis is performed. Through our comprehensive evaluation of different categories of social bots using two benchmark datasets, we were able to demonstrate some achivement that could be utilized in future works.