Steering Bayesian Inference and Decisions through Data Poisoning
Organizations: CUNEF Universidad, Madrid, Spain · Air Force Institute of Technology, OH, USA · University of Arkansas, AR, USA · Machine Learning Group, Universidad Autónoma de Madrid, Spain
Abstract
Adversarial machine learning has revealed that statistical models can be manipulated through poisoned data, and Bayesian inference is no exception. Earlier work has shown that subtle poisoning attacks can drive the posterior toward a distribution of the attacker's choosing. Such posterior attraction attacks require a fully specified target posterior; however, attackers typically care about only a few posterior quantities or, more consequentially, about a downstream decision. Herein, we study how an attacker can alter Bayesian inference and decisions by deleting or replicating a few observations, chosen to minimize the maximum mean discrepancy between the resulting posterior and a target distribution. A suitable kernel lets the attacker steer selected posterior moments without specifying the rest of the target. Because Bayes actions depend on the posterior only through expected utilities, which are themselves posterior moments, the same approach can target a decision directly. We construct the attacks with a gradient-based heuristic that requires only posterior samples, and analyze its convergence. Experiments with regression and hierarchical models compare moment-based and full-posterior attacks, and illustrate how deleting a handful of observations can flip a Bayesian decision.
Figures & tables
Appendix figures & tables8 assets
Supplementary material from the paper’s appendix.
Appendix
Data Poisoning Attacks
Data poisoning attacks manipulate training or retrieval data to corrupt model behavior, implant backdoors, or undermine reliability.
See all 136 papers