Aug 20, 2021 · We propose the adaptively scaled adversarial training (ASAT) in time series analysis, by rescaling data at different time slots with adaptive scales.

Feb 14, 2023 · We propose the adaptively scaled adversarial training (ASAT) in time series analysis, by rescaling data at different time slots with adaptive scales.

Feb 14, 2023 · Experimental results show that the proposed ASAT can improve both the generalization ability and the adversarial robustness of neural networks ...

Dec 21, 2022 · Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples.

Experimental results show that the proposed ASAT can improve both the accuracy and the adversarial robustness of neural networks. Besides enhancing neural ...

Experimental results show that the proposed ASAT can improve both the generalization ability and the adversarial robustness of neural networks ...

ATLGP [21] accelerates the adversarial training with loss guided propagation, but it just can maintain instead of improving the robustness of the model.

This work analyzes the feasibility of generating spiking time series patterns appearing in the banking environment using Generative Adversarial Networks, ...

Apr 25, 2024 · ASAT: Adaptively scaled adversarial training in time series. Neurocomputing 522: 11-23 (2023). [i8]. view. electronic edition via DOI (open ...

Oct 19, 2023 · Adversarial training is a learning technique that improves the robustness of deep neural networks by exposing them to adversarial examples ...