Mixed Strategy Game Model Against Data Poisoning Attacks

06/07/2019
by   Yifan Ou, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/14/2019

When Nash Meets Stackelberg

We analyze Nash games played among leaders of Stackelberg games (), and ...
research
03/28/2022

Adaptive Learning with Artificial Barriers Yielding Nash Equilibria in General Games

Artificial barriers in Learning Automata (LA) is a powerful and yet unde...
research
12/01/2020

Wireless Secret Sharing Game between Two Legitimate Users and an Eavesdropper

Wireless secret sharing is crucial to information security in the era of...
research
11/20/2020

Continuous Blackjack: Equilibrium, Deviation and Adaptive Strategy

We introduce a variant of the classic poker game blackjack – the continu...
research
03/18/2019

A Network Monitoring Game with Heterogeneous Component Criticality Levels

We consider an attacker-operator game for monitoring a large-scale netwo...
research
11/29/2020

Minimax Sample Complexity for Turn-based Stochastic Game

The empirical success of Multi-agent reinforcement learning is encouragi...
research
10/21/2020

On Information Asymmetry in Competitive Multi-Agent Reinforcement Learning: Convergence and Optimality

In this work, we study the system of interacting non-cooperative two Q-l...

Please sign up or login with your details

Forgot password? Click here to reset