Adversarial Online Learning

Abstract

This memorandum report is a summary of the research results of the NRL base-funded project, Adversarial Online Learning, which was funded from FY2017 through FY2020. The principal objective was to research and demonstrate the security vulnerabilities of online machine learning algorithms, supported by game-theoretical analysis and computational methods for exploitation and counter-measures.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 03, 2020
Accession Number
AD1117469

Entities

People

  • Joseph B. Collins
  • Prithviraj Dasgupta

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy
  • Cyber

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Computational Science
  • Cybersecurity
  • Data Mining
  • Data Sets
  • Deep Learning
  • Department Of Defense
  • Detection
  • Detectors
  • Electronic Mail
  • Game Theory
  • Information Processing
  • Information Systems
  • Machine Learning
  • Malware
  • Mathematical Models
  • Military Research
  • Multiagent Systems
  • Network Science
  • Neural Networks
  • Reinforcement Learning

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Neural Network Machine Learning.
  • Technical Research and Report Writing.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms