Date of Award


Document Type

Thesis (Ph.D.)


Department of Computer Science

First Advisor

Sean W. Smith


Well-intentioned decisions---even ones intended to improve aggregate security--- may inadvertently jeopardize security objectives. Adopting a stringent password composition policy ostensibly yields high-entropy passwords; however, such policies often drive users to reuse or write down passwords. Replacing URLs in emails with "safe" URLs that navigate through a gatekeeper service that vets them before granting user access may reduce user exposure to malware; however, it may backfire by reducing the user's ability to parse the URL or by giving the user a false sense of security if user expectations misalign with the security checks delivered by the vetting process. A short timeout threshold may ensure the user is promptly logged out when the system detects they are away; however, if an infuriated user copes by inserting a USB stick in their computer to emulate mouse movements, then not only will the detection mechanism fail but the insertion of the USB stick may present a new attack surface. These examples highlight the disconnect between decision-maker intentions and decision outcomes. Our focus is on bridging this gap. This thesis explores six projects bound together by the core objective of empowering people to make decisions that achieve their security and privacy objectives. First, we use grounded theory to examine Amazon reviews of password logbooks and to obtain valuable insights into users' password management beliefs, motivations, and behaviors. Second, we present a discrete-event simulation we built to assess the efficacy of password policies. Third, we explore the idea of supplementing language-theoretic security with human-computability boundaries. Fourth, we conduct an eye-tracking study to understand users' visual processes while parsing and classifying URLs. Fifth, we discuss preliminary findings from a study conducted on Amazon Mechanical Turk to examine why users fall for unsafe URLs. And sixth, we develop a logic-based representation of mismorphisms, which allows us to express the root causes of security problems. Each project demonstrates a key technique that can help in bridging the gap between intent and outcome.


Originally posted in the Dartmouth College Computer Science Technical Report Series, number TR2020-880.