Adversarial Robustness of Deep Convolutional Candlestick Learner
This addresses adversarial robustness for financial trading applications, but appears incremental as it builds on existing adversarial training methods.
The paper tackles the problem of adversarial attacks on deep learning models in financial trading by developing a method to construct perturbed examples that boost model robustness, resulting in increased stability for candlestick classification.
Deep learning (DL) has been applied extensively in a wide range of fields. However, it has been shown that DL models are susceptible to a certain kinds of perturbations called \emph{adversarial attacks}. To fully unlock the power of DL in critical fields such as financial trading, it is necessary to address such issues. In this paper, we present a method of constructing perturbed examples and use these examples to boost the robustness of the model. Our algorithm increases the stability of DL models for candlestick classification with respect to perturbations in the input data.