A Password System Based on Sketches

Abstract

Text-based passwords are not necessarily as secure as they appear because the protocols required for a secure password are typically ignored for a more user-friendly one. In this paper, we propose a new sketch-based password system that uses biometric data and provides exceptional tradeoff between security and usability. By extending a shape recognition algorithm called Simple K-Space (SKS), a system that is capable of being both secure and robust is developed. In theory and experimentation, new insights into the SKS philosophy are provided, including uniqueness of the model and tolerance of the framework. This system is compared with a state-of-the-art graphical password system using Dynamic Time Warping (DTW) and found to achieve comparable performance without using any biometrics. The addition of biometrics substantially increased the level of performance, reducing the equal error rate (EER) by more than 12%

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 12, 2016
Accession Number
AD1020912

Entities

People

  • Ben Riggins
  • Cliff Wang
  • Wes Snyder

Organizations

  • North Carolina State University

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Authentication
  • Automated Speech Recognition
  • Biometric Security
  • Biometrics
  • Computational Complexity
  • Computer Science
  • Computers
  • Databases
  • Engineering
  • Facial Recognition
  • Fingerprint Recognition
  • Fingerprints
  • Recognition
  • Security
  • Students
  • Tablet Computers

Fields of Study

  • Computer science

Readers

  • Database Systems and Applications
  • Speech Processing/Speech Recognition.
  • Systems Analysis and Design

Technology Areas

  • Space