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.
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