Abstract—It is now widely accepted that in many situations where classifiers are deployed, adversaries deliberately manipulate data in order to reduce the classifier’s accura...
Abstract. We present a game-theoretic framework for modeling and solving routing problems in dynamically changing networks. The model covers the aspects of reactivity and non-termi...
We discuss how the interaction between spam senders and e-mail users can be modelled as a two-player adversary game. We show how the resulting model can be used to predict the str...
Ion Androutsopoulos, Evangelos F. Magirou, Dimitri...
This paper introduces a novel multiagent learning algorithm, Convergence with Model Learning and Safety (or CMLeS in short), which achieves convergence, targeted optimality agains...