Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Alpha-wolves and Alpha-mammals: Exploring Dictionary Attacks on Iris Recognition Systems

Sudipta Banerjee, Anubhav Jain, Zehua Jiang, Nasir Memon, Julian Togelius, Arun Ross

TL;DR

An hitherto unknown vulnerability wherein IrisCodes are mixed using simple bit-wise operators to generate alpha-mixtures -alpha-wolves (combining a set of “wolf” samples) and alpha-mammals (combining a set of users selected via search optimization) that increase false matches is presented.

Abstract

A dictionary attack in a biometric system entails the use of a small number of strategically generated images or templates to successfully match with a large number of identities, thereby compromising security. We focus on dictionary attacks at the template level, specifically the IrisCodes used in iris recognition systems. We present an hitherto unknown vulnerability wherein we mix IrisCodes using simple bitwise operators to generate alpha-mixtures - alpha-wolves (combining a set of "wolf" samples) and alpha-mammals (combining a set of users selected via search optimization) that increase false matches. We evaluate this vulnerability using the IITD, CASIA-IrisV4-Thousand and Synthetic datasets, and observe that an alpha-wolf (from two wolves) can match upto 71 identities @FMR=0.001%, while an alpha-mammal (from two identities) can match upto 133 other identities @FMR=0.01% on the IITD dataset.

Alpha-wolves and Alpha-mammals: Exploring Dictionary Attacks on Iris Recognition Systems

TL;DR

An hitherto unknown vulnerability wherein IrisCodes are mixed using simple bit-wise operators to generate alpha-mixtures -alpha-wolves (combining a set of “wolf” samples) and alpha-mammals (combining a set of users selected via search optimization) that increase false matches is presented.

Abstract

A dictionary attack in a biometric system entails the use of a small number of strategically generated images or templates to successfully match with a large number of identities, thereby compromising security. We focus on dictionary attacks at the template level, specifically the IrisCodes used in iris recognition systems. We present an hitherto unknown vulnerability wherein we mix IrisCodes using simple bitwise operators to generate alpha-mixtures - alpha-wolves (combining a set of "wolf" samples) and alpha-mammals (combining a set of users selected via search optimization) that increase false matches. We evaluate this vulnerability using the IITD, CASIA-IrisV4-Thousand and Synthetic datasets, and observe that an alpha-wolf (from two wolves) can match upto 71 identities @FMR=0.001%, while an alpha-mammal (from two identities) can match upto 133 other identities @FMR=0.01% on the IITD dataset.
Paper Structure (15 sections, 2 equations, 6 figures, 13 tables, 1 algorithm)

This paper contains 15 sections, 2 equations, 6 figures, 13 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminaries
  4. Morphing vs. Mixing
  5. Proposed Method
  6. Method I: Generating Alpha-wolves
  7. Method II: Generating Alpha-mammals
  8. Experimental Design
  9. Results and Analysis
  10. Results for Method I: Alpha-wolves
  11. Results for Method II: Alpha-mammals
  12. Discussion
  13. Analyzing alpha-mixtures
  14. Additional analysis
  15. Conclusion

Figures (6)

  • Figure 1: Examples of wolves used in generating alpha-wolves belonging to IITD (top row), CASIA-IrisV4-Thousand (middle row) and CASIA-IrisV4-Synthetic (bottom row) datasets. Note that, visually, wolves are high quality iris images.
  • Figure 2: Example of an alpha-mammal computed on the IITD dataset wherein a majority of the IrisCode is covered by the mask.
  • Figure 3: Distribution of 1's and 0's of alpha-wolves using two wolves for IITD $lg$-Right (left) and CASV4-Th $qsw$-Right (right).
  • Figure 4: Examples of the heatmap of '0's and '1's frequency.
  • Figure 5: Illustration of alpha-wolf translated iris image (top row) and the respective constituent seed wolves (bottom two rows) along with their IrisCodes and masks.
  • ...and 1 more figures