Explainable Deep Anomaly Detection with Input Perturbation
Abstract
The PI, Dr. Y. Raymond Fu, is researching anomaly detection in machine learning. Anomalies, also known as outliers, are defined as data instances that deviate from the norm of data instances in a sample space. Correspondingly, anomaly detection (AD) refers to the process of finding these anomalous data points out in a data-driven fashion, which has long been a fundamental problem in machine learning and has various real-world applications, such as medical health, fraud detection, cybersecurity and video surveillance. Unsupervised anomaly detection (UAD), which is the most common and challenging case, obeys the condition that solely unlabeled data with both inliers and outliers are provided, and the anomaly detection technique is required to be capable of detecting the outliers.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Feb 29, 2024
- Source ID
- FA95502310290
Entities
People
- Yun Fu
Organizations
- Air Force Office of Scientific Research
- Northeastern University
- United States Air Force