Generative adversarial networks for spatio-temporal data: A survey
Generative Adversarial Networks (GANs) have shown remarkable success in producing
realistic-looking images in the computer vision area. Recently, GAN-based techniques are …
realistic-looking images in the computer vision area. Recently, GAN-based techniques are …
Evaluating robustness of predictive uncertainty estimation: Are Dirichlet-based models reliable?
AK Kopetzki, B Charpentier, D Zügner… - International …, 2021 - proceedings.mlr.press
Dirichlet-based uncertainty (DBU) models are a recent and promising class of uncertainty-
aware models. DBU models predict the parameters of a Dirichlet distribution to provide fast …
aware models. DBU models predict the parameters of a Dirichlet distribution to provide fast …
Robust probabilistic time series forecasting
Probabilistic time series forecasting has played critical role in decision-making processes
due to its capability to quantify uncertainties. Deep forecasting models, however, could be …
due to its capability to quantify uncertainties. Deep forecasting models, however, could be …
Adversarial machine learning and adversarial risk analysis in multi-source command and control
WN Caballero, M Friend… - Signal Processing, Sensor …, 2021 - spiedigitallibrary.org
Over the last decade, various defense and security agencies have focused on methods of
data and information fusion across multiple domains (eg, space, air, land, sea, undersea …
data and information fusion across multiple domains (eg, space, air, land, sea, undersea …
Adversarial robustness of amortized Bayesian inference
Bayesian inference usually requires running potentially costly inference procedures
separately for every new observation. In contrast, the idea of amortized Bayesian inference …
separately for every new observation. In contrast, the idea of amortized Bayesian inference …
TSadv: Black-box adversarial attack on time series with local perturbations
W Yang, J Yuan, X Wang, P Zhao - Engineering Applications of Artificial …, 2022 - Elsevier
Deep neural networks (DNNs) for time series classification have potential security concerns
due to their vulnerability to adversarial attacks. Previous work that perturbs time series …
due to their vulnerability to adversarial attacks. Previous work that perturbs time series …
Why did this model forecast this future? information-theoretic saliency for counterfactual explanations of probabilistic regression models
C Raman, A Nonnemaker… - Advances in …, 2024 - proceedings.neurips.cc
We propose a post hoc saliency-based explanation framework for counterfactual reasoning
in probabilistic multivariate time-series forecasting (regression) settings. Building upon …
in probabilistic multivariate time-series forecasting (regression) settings. Building upon …
Multiple agents' spatiotemporal data generation based on recurrent regression dual discriminator GAN
P Bao, Z Chen, J Wang, D Dai - Neurocomputing, 2022 - Elsevier
Abstract Generative Adversarial Networks (GANs) have proven their capability of generating
realistic-looking data and have been widely used in image related and time-series …
realistic-looking data and have been widely used in image related and time-series …
Targeted Attacks on Timeseries Forecasting
Real-world deep learning models developed for Time Series Forecasting are used in
several critical applications ranging from medical devices to the security domain. Many …
several critical applications ranging from medical devices to the security domain. Many …
AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series Forecasting
Y Lin - 2023 IEEE 10th International Conference on Data …, 2023 - ieeexplore.ieee.org
Multi-horizon time series forecasting, crucial across diverse domains, demands high
accuracy and speed. While AutoRegressive (AR) models excel in short-term predictions …
accuracy and speed. While AutoRegressive (AR) models excel in short-term predictions …