Mixed Strategy Game Model Against Data Poisoning Attacks

TL;DR

This paper models data poisoning attacks using game theory, proving the absence of pure strategy equilibria, and proposes a mixed strategy approach with an algorithm to defend effectively, validated through experiments.

Contribution

It introduces a game-theoretic model for data poisoning attacks and develops an algorithm for mixed strategy defense, addressing the lack of pure strategy equilibria.

Findings

Pure strategy Nash Equilibrium does not exist in the model.

The mixed strategy defense strategy is effective in experiments.

The proposed algorithm approximates Nash Equilibrium strategies.

Abstract

In this paper we use game theory to model poisoning attack scenarios. We prove the non-existence of pure strategy Nash Equilibrium in the attacker and defender game. We then propose a mixed extension of our game model and an algorithm to approximate the Nash Equilibrium strategy for the defender. We then demonstrate the effectiveness of the mixed defence strategy generated by the algorithm, in an experiment.