DeepAI AI Chat
Log In Sign Up

SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning

by   Maxwell Standen, et al.

Multi-Agent Reinforcement Learning (MARL) is vulnerable to Adversarial Machine Learning (AML) attacks and needs adequate defences before it can be used in real world applications. We have conducted a survey into the use of execution-time AML attacks against MARL and the defences against those attacks. We surveyed related work in the application of AML in Deep Reinforcement Learning (DRL) and Multi-Agent Learning (MAL) to inform our analysis of AML for MARL. We propose a novel perspective to understand the manner of perpetrating an AML attack, by defining Attack Vectors. We develop two new frameworks to address a gap in current modelling frameworks, focusing on the means and tempo of an AML attack against MARL, and identify knowledge gaps and future avenues of research.


page 1

page 2

page 3

page 4


Enhancing the Robustness of QMIX against State-adversarial Attacks

Deep reinforcement learning (DRL) performance is generally impacted by s...

A further exploration of deep Multi-Agent Reinforcement Learning with Hybrid Action Space

The research of extending deep reinforcement learning (drl) to multi-age...

Evolution of a Complex Predator-Prey Ecosystem on Large-scale Multi-Agent Deep Reinforcement Learning

Simulation of population dynamics is a central research theme in computa...

Learning to Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding

Multi-agent pathfinding (MAPF) is a critical field in many large-scale r...

Survey on Multi-Agent Q-Learning frameworks for resource management in wireless sensor network

This report aims to survey multi-agent Q-Learning algorithms, analyze di...

Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks

Recent exploration of the multi-agent backdoor attack demonstrated the b...

Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS

Cyber attacks are increasing in volume, frequency, and complexity. In re...