English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Applying neural network (NN) methods in games can lead to various new andexciting game dynamics not previously possible. However, they also lead to newchallenges such as the lack of large, clean datasets, varying player skilllevels, and changing gameplay strategies. In this paper, we focus on theadversarial player strategy aspect in the game iNNk, in which players try tocommunicate secret code words through drawings with the goal of not beingdeciphered by a NN. Some strategies exploit weaknesses in the NN thatconsistently trick it into making incorrect classifications, leading tounbalanced gameplay. We present a method that combines transfer learning andensemble methods to obtain a data-efficient adaptation to these strategies.This combination significantly outperforms the baseline NN across alladversarial player strategies despite only being trained on a limited set ofadversarial examples. We expect the methods developed in this paper to beuseful for the rapidly growing field of NN-based games, which will require newapproaches to deal with unforeseen player creativity.

Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning