We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies
against it, achieving a $> $97% win rate against KataGo running at superhuman settings …

Multi-Agent Reinforcement Learning (MARL) is susceptible to Adversarial Machine Learning
(AML) attacks. Execution-time AML attacks against MARL are complex due to effects that …

If machine learning models were to achieve superhuman abilities at various reasoning or
decision-making tasks, how would we go about evaluating such models, given that humans …

We attack the state-of-the-art Go-playing AI system, KataGo, by training an adversarial policy
that plays against a frozen KataGo victim. Our attack achieves a> 99% win-rate against …

We study automated intrusion response and formulate the interaction between an attacker
and a defender as an optimal stop** game where attack and defense strategies evolve …

This paper proposes Mutation-Driven Multiplicative Weights Update (M2WU) for learning an
equilibrium in two-player zero-sum normal-form games and proves that it exhibits the last …

We study automated intrusion response for an IT infrastructure and formulate the interaction
between an attacker and a defender as a partially observed stochastic game. To solve the …

In this study, we consider a variant of the Follow the Regularized Leader (FTRL) dynamics in
two-player zero-sum games. FTRL is guaranteed to converge to a Nash equilibrium when …

Computational game theory has many applications in the modern world in both adversarial
situations and the optimization of social good. While there exist many algorithms for …

Deep Reinforcement Learning (DRL) is a subfield of machine learning for training
autonomous agents that take sequential actions across complex environments. Despite its …