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

Abstract

Applying neural network (NN) methods in games can lead to various new and exciting game dynamics not previously possible. However, they also lead to new challenges such as the lack of large, clean datasets, varying player skill levels, and changing gameplay strategies. In this paper, we focus on the adversarial player strategy aspect in the game iNNk, in which players try to communicate secret code words through drawings with the goal of not being deciphered by a NN. Some strategies exploit weaknesses in the NN that consistently trick it into making incorrect classifications, leading to unbalanced gameplay. We present a method that combines transfer learning and ensemble methods to obtain a data-efficient adaptation to these strategies. This combination significantly outperforms the baseline NN across all adversarial player strategies despite only being trained on a limited set of adversarial examples. We expect the methods developed in this paper to be useful for the rapidly growing field of NN-based games, which will require new approaches to deal with unforeseen player creativity.

10 pages, 4 Figures. Accepted for publishing at the 16th International Conference on the Foundations of Digital Games (FDG) 2021

References in corpus (9)

• How transferable are features in deep neural networks?
• Language Models are Few-Shot Learners
• Popular Ensemble Methods: An Empirical Study
• Countering Adversarial Images using Input Transformations
• Adversarial Machine Learning at Scale
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• Batch Normalization is a Cause of Adversarial Vulnerability
• Fooling a Real Car with Adversarial Traffic Signs
• A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media