Meta Pattern Concern Score: A Novel Evaluation Measure with Human Values for Multi-classifiers

1 code implementation • 14 Sep 2022 • Yanyun Wang, Dehui Du, YuanHao Liu

And a case study shows it can not only find the ideal model reducing 0. 53% of dangerous cases by only sacrificing 0. 04% of training accuracy, but also refine the learning rate to train a new model averagely outperforming the original one with a 1. 62% lower value of itself and 0. 36% fewer number of dangerous cases.

TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack

2 code implementations • 14 Sep 2022 • Yanyun Wang, Dehui Du, Haibo Hu, Zi Liang, YuanHao Liu

Recent years have witnessed the success of recurrent neural network (RNN) models in time series classification (TSC).

Adversarial Attack Time Series +2