データポイズニングによるベイズ推論と意思決定の操作
Steering Bayesian Inference and Decisions through Data Poisoning
少数の観測データを削除・複製することで、ベイズ事後分布の特定のモーメントや下流の意思決定を攻撃者の意図通りに誘導する手法を提案し、その収束性を解析した研究。
著者: Roi Naveiro, William N. Caballero, Juan Maroñas
分類: stat.ML, cs.LG
原文アブストラクト
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.
