Visible to the public Leveraging the Effects of Cognitive Function on Input Device Analytics to Improve Security - April 2016Conflict Detection Enabled

Submitted by drwright on Thu, 03/10/2016 - 12:03pm

Public Audience
Purpose: To highlight project progress. Information is generally at a higher level which is accessible to the interested public. All information contained in the report (regions 1-3) is a Government Deliverable/CDRL.

PI(s):  David L. Roberts, Robert St. Amant
Researchers: Alok Goel, Ignacio X. Dominguez, Jayant Dhawan

 

HARD PROBLEM(S) ADDRESSED

  • Human Behavior - Our work addresses understanding human behavior through observations of input device usage. The basic principles we are developing will enable new avenues for characterizing risk and identifying malicious (or accidental) uses of systems that lead to security problems. The ultimate goal of our work is the development of a novel class of security proofs that we call "Human Subtlety Proofs" (HSPs). HSPs combine the unobtrusiveness of Human Observational Proofs with the interactivity of Human Interactive Proofs, which hopefully will lead to more secure interactions.

PUBLICATIONS

None this quarter.

ACCOMPLISHMENT HIGHLIGHTS

  • This quarter our emphasis has been on cognitive modeling of the data we have collected. In particular, we completed a comparison of our data to an existing cognitive model to identify any gaps in the existing model. We found significant differences in the empirical data and the data generated by comparison to the existing model. 
  • To further progress towards the implementation and evaluation of Human Subtlety Proofs (HSPs), we have emphasized characterizing the differences between existing cognitive models of typing and the types of tasks users are doing in the data set we have collected. Our research activities this quarter have emphasized both good points and bad points about existing models through a data-driven hypothesis generation process, whereby a custom visualization tool has scaffolded our data analysis and ideation about human subtleties. 
  • We have advanced the development of our novel visualization tool, which allows us to not only visualize interaction data, but also to illustrate what a cognitive model would predict and to characterize how the empirical values in the data would fit into that model. This tool enables our team to carefully examine the ways in which user behavior deviates from expected behaviors, which is exactly how HSP development will progress.  
Groups: