A Special Workshop on AI Safety

Abstract

The objective of this project is to organize an invitational workshop that brings together researchers from academia, government, and industry to discuss important research problems in artificial intelligence (AI) assurance. The workshop will invite eminent researchers in multiple areas relevant to AI assurance, including, but not limited to, machine learning (ML) algorithms, real-time systems, reliability and fault tolerance, distributed systems and networking, trustworthy ML and AI security, and ML applications. The workshop organization will have a combination of keynote talks, panel discussions, and world cafe type of brainstorming. The outcome of the workshop is the identification of key research challenges facing the AI assurance community and possible path forward to addressing them. The findings and research agenda resulting from this workshop can eventually help the Army scientists, engineers, program managers, and contractors developing and deploying much more reliable AI-based systems.

Document Details

Document Type
DoD Grant Award
Publication Date
Aug 31, 2020
Source ID
W911NF2010319

Entities

People

  • Wenjing Lou

Organizations

  • Army Contracting Command
  • United States Army
  • Virginia Tech

Tags

Fields of Study

  • Computer science

Readers

  • Academic Conference Management
  • Cybersecurity.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy