|Institution:||University of Pittsburgh|
|Full text PDF:||http://d-scholarship.pitt.edu/26802/1/Baracaldo_ETD-final.pdf|
Insider Attacks are one of the most dangerous threats organizations face today. An insider attack occurs when a person authorized to perform certain actions in an organization decides to abuse the trust, and harm the organization by causing breaches in the confidentiality, integrity or availability of the organization’s assets. These attacks may negatively impact the reputation of the organization, its productivity, and may incur heavy losses in revenue and clients. Preventing insider attacks is a daunting task. Employees need legitimate access to effectively perform their jobs; however, at any point of time they may misuse their privileges accidentally or intentionally. Hence, it is necessary to develop a system capable of finding a middle ground where the necessary privileges are provided and insider threats are mitigated. In this dissertation, we address this critical issue. We propose three adaptive risk-and-trust aware access control frameworks that aim at thwarting insider attacks by incorporating the behavior of users in the access control decision process. Our first framework is tailored towards general insider threat prevention in role-based access control systems. As part of this framework, we propose methodologies to specify risk-and-trust aware access control policies and a risk management approach that minimizes the risk exposure for each access request. Our second framework is designed to mitigate the risk of obligation-based systems which are difficult to manage and are particularly vulnerable to sabotage. As part of our obligation-based framework, we propose an insider-threat-resistant trust computation methodology. We emphasize the use of monitoring of obligation fulfillment patterns to determine some psychological precursors that have high predictive power with respect to potential insider threats. Our third framework is designed to take advantage of geo-social information to deter insider threats. We uncover some insider threats that arise when geo-social information is used to make access control decisions. Based on this analysis, we define an insider threat resilient access control approach to manage privileges that considers geo-social context. The models and methodologies presented in this dissertation can help a broad range of organizations in mitigating insider threats.