Detecting and Quantifying Malicious Activity with Simulation-based Inference

TL;DR

This paper introduces a probabilistic programming approach to identify and measure the impact of malicious users in recommendation systems, offering structured insights and damage quantification.

Contribution

It presents a novel application of probabilistic programming for malicious user detection and introduces a simulation-based metric for impact assessment.

Findings

Effective identification of malicious users demonstrated

Quantification of malicious impact achieved

Structured modeling of user behavior provided

Abstract

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.