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

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Cyber
  • Space
  • Space - Space Objects