Robustness and Vulnerability Measurement of Deep Learning Methods for Cyber Defense

Abstract

The goal of this study is to investigate mathematical concepts and quantitative measures of robustness and vulnerability of machine learning systems to adversarial data and develop computational methods capable of quantitatively evaluating the robustness and vulnerability of deep learning tools that can be applied in cybersecurity settings. The first phase of the project is a literature review. The second phase of the study is focused on robustness analysis of infrastructure cyber security. Using a microgrid power system model and learning-based fault detection as the testbed, we investigate the robustness of neural networks subjected to noisy or poisoned data. Finally, the third phase of the project, explores distributional robustness. Neural networks may sometimes be used outside of the environment in which they were trained. If the distribution of the incoming data is significantly different from that of the training data, it could negatively impact the performance of the neural network. In addition to a quantitative analysis of robustness, the study reveals an underlying relationship between the robustness and the dynamical behavior the training data.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2022
Accession Number
AD1194685

Entities

People

  • Elana Kozak
  • Phillip Smith
  • Thor Martinsen
  • Wei Kang

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Autonomy
  • Cyber
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Applied Mathematics
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computational Science
  • Computer Languages
  • Cyber Defense Techniques
  • Cyberattacks
  • Cybersecurity
  • Data Mining
  • Data Science
  • Deep Learning
  • Detection
  • Image Classification
  • Information Processing
  • Information Science
  • Information Systems
  • Intrusion Detectors
  • Machine Learning
  • Neural Networks

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks
  • Cyber