Detecting and Quantifying Malicious Activity with Simulation-based Inference
This work addresses security and integrity issues in recommendation systems for platform operators, presenting an incremental improvement through a new quantification method.
The paper tackles the problem of identifying malicious users in recommendation algorithms by using probabilistic programming to model user interactions and quantify damage, demonstrating experiments with a novel simulation-based measure for assessing user impact.
We propose the use of probabilistic programming techniques to tackle the malicious user identification problem in a recommendation algorithm. Probabilistic programming provides numerous advantages over other techniques, including but not limited to providing a disentangled representation of how malicious users acted under a structured model, as well as allowing for the quantification of damage caused by malicious users. We show experiments in malicious user identification using a model of regular and malicious users interacting with a simple recommendation algorithm, and provide a novel simulation-based measure for quantifying the effects of a user or group of users on its dynamics.