ExAD: An Ensemble Approach for Explanation-based Adversarial Detection

no code implementations • 22 Mar 2021 • Raj Vardhan, Ninghao Liu, Phakpoom Chinprutthiwong, Weijie Fu, Zhenyu Hu, Xia Ben Hu, Guofei Gu

Several defense methods have been proposed against adversarial attacks to detect adversarial examples at test time or to make machine learning models more robust.

BIG-bench Machine Learning

Neighborhood Structure Assisted Non-negative Matrix Factorization and its Application in Unsupervised Point-wise Anomaly Detection

no code implementations • 17 Jan 2020 • Imtiaz Ahmed, Xia Ben Hu, Mithun P. Acharya, Yu Ding

Dimensionality reduction is considered as an important step for ensuring competitive performance in unsupervised learning such as anomaly detection.

Anomaly Detection Dimensionality Reduction