Who's behind these predictions? Reconciling transparency and privacy in machine learning

Abstract

The PI completed this project investigating the tradeoff between external query and response access to machine learning (ML) models while preserving security and confidentiality. The objective was to use queries and responses from an unknown ML model to discover the model family (neural net, decision tree, support vector machine, generalized linear model, etc.) of the unknown model. This represents a security risk as attackers can leverage known aspects of a ML model to inject adversarial examples during training and/or model deployment. The main idea was to train surrogate models based on the inputs and outputs of the unknown model. The PI then employed a dissimilarity measure (as specified in the attached final report) to determine which surrogate model best matched input-output data from the unknown model. The results show such an approach has potential as they were able to correctly identify model families much better than random chance, but there remains much room for further investigation. More specifics may be found in the attached final report and the technical papers reference therein.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 14, 2019
Accession Number
AD1077647

Entities

People

  • María José Quintana Hernández

Organizations

  • Technical University of Valencia

Tags

Communities of Interest

  • Autonomy
  • Space

DTIC Thesaurus Topics

  • Agreements
  • Air Force
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Artificial Neural Networks
  • Data Set
  • Department Of Defense
  • Digital Data
  • Discriminant Analysis
  • Facial Recognition
  • Identification
  • Information Science
  • Learning
  • Machine Learning
  • Networks
  • Neural Networks
  • Scientific Research
  • Security
  • Supervised Machine Learning
  • Taxonomy
  • Test Sets
  • Training

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Cybersecurity.
  • Neural Network Machine Learning.

Technology Areas

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