Self-supervised learning for time series analysis: Taxonomy, progress, and prospects

K Zhang, Q Wen, C Zhang, R Cai, M **… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Self-supervised learning (SSL) has recently achieved impressive performance on various
time series tasks. The most prominent advantage of SSL is that it reduces the dependence …

A survey on time-series pre-trained models

Q Ma, Z Liu, Z Zheng, Z Huang, S Zhu… - … on Knowledge and …, 2024 - ieeexplore.ieee.org
Time-Series Mining (TSM) is an important research area since it shows great potential in
practical applications. Deep learning models that rely on massive labeled data have been …

When deep learning-based soft sensors encounter reliability challenges: a practical knowledge-guided adversarial attack and its defense

R Guo, H Liu, D Liu - IEEE Transactions on Industrial …, 2023 - ieeexplore.ieee.org
Deep learning-based soft sensors (DLSSs) have been demonstrated to exhibit significantly
improved sensing accuracy; however, their vulnerability to adversarial attacks affects their …

Backtime: Backdoor attacks on multivariate time series forecasting

X Lin, Z Liu, D Fu, R Qiu… - Advances in Neural …, 2025 - proceedings.neurips.cc
Abstract Multivariate Time Series (MTS) forecasting is a fundamental task with numerous
real-world applications, such as transportation, climate, and epidemiology. While a myriad of …

Similarity-based integrity protection for deep learning systems

R Hou, S Ai, Q Chen, H Yan, T Huang, K Chen - Information Sciences, 2022 - Elsevier
Deep learning technologies have achieved remarkable success in various tasks, ranging
from computer vision, object detection to natural language processing. Unfortunately, state …

Towards robust learning with noisy and pseudo labels for text classification

M Ahmed, B Wen, L Ao, S Pan, J Su, X Cao, Y Liu - Information Sciences, 2024 - Elsevier
Abstract Unlike Positive Training (PT), Negative Training (NT) is an indirect learning
technique that trains the model on a combination of clean and noisy data using …

AGS: Transferable adversarial attack for person re-identification by adaptive gradient similarity attack

Z Tao, Z Lu, J Peng, H Wang - Knowledge-Based Systems, 2024 - Elsevier
Person re-identification (Re-ID) has achieved tremendous success in the fields of computer
vision and security. However, Re-ID models are susceptible to adversarial examples, which …

3d adversarial attacks beyond point cloud

J Zhang, L Chen, B Liu, B Ouyang, Q **e, J Zhu, W Li… - Information …, 2023 - Elsevier
Recently, 3D deep learning models have been shown to be susceptible to adversarial
attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks …

Economic system forecasting based on temporal fusion transformers: Multi-dimensional evaluation and cross-model comparative analysis

Y Han, Y Tian, L Yu, Y Gao - Neurocomputing, 2023 - Elsevier
Although helpful in reducing the uncertainty associated with economic activities, economic
forecasting often suffers from low accuracy. Recognizing the high compatibility between …

ERGCN: Data enhancement-based robust graph convolutional network against adversarial attacks

T Wu, N Yang, L Chen, X **ao, X **an, J Liu, S Qiao… - Information …, 2022 - Elsevier
With recent advancements, graph neural networks (GNNs) have shown considerable
potential for various graph-related tasks, and their applications have gained considerable …