Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 66 references that are in the map. First posted on arXiv 5 Jul 2021.
Builds on
29 of 66 references.
References · 29
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2014How transferable are features in deep neural networks?cited by 1,216
- 2016Adversarial Machine Learning at Scalecited by 934
- 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
- 2017One pixel attack for fooling deep neural networkscited by 579
17 more
- 2018Generative Image Inpainting with Contextual Attentioncited by 578
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
- 2018A Survey on Deep Transfer Learningcited by 417
- 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
- 2016Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learningcited by 209
- 2018Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objectscited by 143
- 2019A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Mediacited by 95
- 2018Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Networkcited by 76
- 2020Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Networkcited by 51
- 2015A Unified Gradient Regularization Family for Adversarial Examplescited by 43
- 2019Fooling a Real Car with Adversarial Traffic Signscited by 29
- 2019Batch Normalization is a Cause of Adversarial Vulnerabilitycited by 28
- 2020TOAD-GAN: Coherent Style Level Generation from a Single Examplecited by 22
- 2017Robustness to Adversarial Examples through an Ensemble of Specialistscited by 21
- 2021Player-AI Interaction: What Neural Network Games Reveal About AI as Playcited by 8
- 2020iNNk: A Multi-Player Game to Deceive a Neural Networkcited by 2
Built on by
Not cited yet.