Detecting and Quantifying Malicious Activity with Simulation-based Inference
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.
Cite
@article{arxiv.2110.02483,
title = {Detecting and Quantifying Malicious Activity with Simulation-based Inference},
author = {Andrew Gambardella and Bogdan State and Naeemullah Khan and Leo Tsourides and Philip H. S. Torr and Atılım Güneş Baydin},
journal= {arXiv preprint arXiv:2110.02483},
year = {2021}
}
Comments
Short version, appeared at ICML workshop on Socially Responsible Machine Learning 2021