The authors define a sequence-level coverage coefficient, claim exponential error amplification, and use rare-pattern deletion to poison offline RL datasets.
SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning
The authors define a sequence-level coverage coefficient, claim exponential error amplification, and use rare-pattern deletion to poison offline RL datasets.