Summaries - Research
Back On-Phone Multimodal Continuous, Active Authentication
|Division||Research & Sponsored Programs|
|Investigator(s)||Martell, Craig H.|
|Sponsor||National Reconnaissance Office (DoD)|
As mobile devices become both ubiquitous and highly personal, the idea of continuous, active authentication has become very popular. Leveraging our previous work with on-phone, lightweight NLP-based biometrics (i.e. SMS authorship identification), we are interesting in expanding and developing our tool suite to handle other methods for continuous authentication.
The objective is to validate whether simple methods can be effective in the context of multiple signals. We will select signals for continuous authentication that have been explored previously in the literature (but in isolation), including SMS authorship, keystroke dynamics, gait analysis, and access-point fingerprinting. These signals leverage popular devices found in most mobile devices: software keyboard, accelerometer, GPS, wireless antennae, etc. We will prototype the collection and analysis software, and release it as open-source so that other researchers can innovate with the same framework and validate new ideas in the field.
|Publications||Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal|
|Data||Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal|