Calfat: Calibrated federated adversarial training with label skewness

C Chen, Y Liu, X Ma, L Lyu - Advances in Neural …, 2022 - proceedings.neurips.cc
Recent studies have shown that, like traditional machine learning, federated learning (FL) is
also vulnerable to adversarial attacks. To improve the adversarial robustness of FL …

Structural tensor learning for event identification with limited labels

H Li, Z Ma, Y Weng, E Blasch… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The increasing uncertainty of distributed energy resources promotes the risks of transient
events for power systems. To capture event dynamics, Phasor Measurement Unit (PMU) …

Improving adversarial robustness with self-paced hard-class pair reweighting

P Hou, J Han, X Li - Proceedings of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Abstract Deep Neural Networks are vulnerable to adversarial attacks. Among many defense
strategies, adversarial training with untargeted attacks is one of the most effective methods …

Maximization of average precision for deep learning with adversarial ranking robustness

G Li, W Tong, T Yang - Advances in Neural Information …, 2024 - proceedings.neurips.cc
This paper seeks to address a gap in optimizing Average Precision (AP) while ensuring
adversarial robustness, an area that has not been extensively explored to the best of our …

Doubly Robust Instance-Reweighted Adversarial Training

D Sow, S Lin, Z Wang, Y Liang - arXiv preprint arXiv:2308.00311, 2023 - arxiv.org
Assigning importance weights to adversarial data has achieved great success in training
adversarially robust networks under limited model capacity. However, existing instance …

It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness

P Xiong, M Tegegn, JS Sarin, S Pal, J Rubin - ACM Computing Surveys, 2024 - dl.acm.org
Adversarial examples are inputs to machine learning models that an attacker has
intentionally designed to confuse the model into making a mistake. Such examples pose a …

Adversarial examples for extreme multilabel text classification

M Qaraei, R Babbar - Machine Learning, 2022 - Springer
Abstract Extreme Multilabel Text Classification (XMTC) is a text classification problem in
which,(i) the output space is extremely large,(ii) each data point may have multiple positive …

A Mix-up Strategy to Enhance Adversarial Training with Imbalanced Data

W Wang, H Shomer, Y Wan, Y Li, J Huang… - Proceedings of the 32nd …, 2023 - dl.acm.org
Adversarial training has been proven to be one of the most effective techniques to defend
against adversarial examples. The majority of existing adversarial training methods assume …

Fair Robust Active Learning by Joint Inconsistency

TH Wu, HT Su, ST Chen… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We introduce a new learning framework, Fair Robust Active Learning (FRAL), generalizing
conventional active learning to fair and adversarial robust scenarios. This framework …

Imbalanced Flight Test Sensor Temporal Data Anomaly Detection

D Zhang, H Yang, J Gao, X Li - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The functioning of flight test sensors is crucial for aviation safety, but previous methods often
overlooked the impact of data imbalance on model performance while exploring anomalies …