Security Questions to Ask Your Data Scientists

Abstract

Contents include: AI/ML Security Challenge ; AI/ML Development differs from Software Development ; AI/ML Security differs from Software Security ; Bridging the Gap ; Protecting AI/ML Systems ; Machine Learning and Deep Learning ; There are Different Types of ML ; If You use the Wrong Math, You can get Pure Nonsense ; MLOps ; Notional ML Pipeline ; AI/ML Security Threats ; Adversarial Machine Learning ; Failure Modes Table ; Data Attacks ; Questions to Ask Your Data Scientists - Data ; Model Attacks ; Questions to Ask Your Data Scientists - Model ; Questions to Ask Your Data Scientists - Software.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 23, 2022
Accession Number
AD1180863

Entities

People

  • Thomas Scanlon

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy
  • Cyber

DTIC Thesaurus Topics

  • Algorithms
  • Anomaly Detection
  • Artificial Intelligence
  • Bayesian Networks
  • Change Detection
  • Configuration Management
  • Copyrights
  • Cyberattacks
  • Data Science
  • Data Sets
  • Deep Learning
  • Denial Of Service Attack
  • Detection
  • Engineering
  • Failure Mode And Effect Analysis
  • Governments
  • Information Science
  • Learning
  • Machine Learning
  • Neural Networks
  • Software Development
  • Training

Fields of Study

  • Computer science

Readers

  • Cybersecurity.
  • Neural Network Machine Learning.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks