Characterizing and measuring maliciousness for cybersecurity risk assessment

Cyber attacks have been increasingly detrimental to networks, systems, and users, and are increasing in number and severity globally. To better predict system vulnerabilities, cybersecurity researchers are developing new and more holistic approaches to characterizing cybersecurity system risk. The process must include characterizing the human factors that contribute to cyber security vulnerabilities and risk. Rationality, expertise, and maliciousness are key human characteristics influencing cyber risk within this context, yet maliciousness is poorly characterized in the literature. There is a clear absence of literature pertaining to human factor maliciousness as it relates to cybersecurity and only limited literature relating to aspects of maliciousness in other disciplinary literatures, such as psychology, sociology, and law. In an attempt to characterize human factors as a contribution to cybersecurity risk, the Cybersecurity Collaborative Research Alliance (CSec-CRA) has developed a Human Factors risk framework. This framework identifies the characteristics of an attacker, user, or defender, all of whom may be adding to or mitigating against cyber risk. The maliciousness literature and the proposed maliciousness assessment metrics are discussed within the context of the Human Factors Framework and Ontology. Maliciousness is defined as the intent to harm. Most maliciousness cyber research to date has focused on detecting malicious software but fails to analyze an individual’s intent to do harm to others by deploying malware or performing malicious attacks. Recent efforts to identify malicious human behavior as it relates to cybersecurity, include analyzing motives driving insider threats as well as user profiling analyses. However, cyber-related maliciousness is neither well-studied nor is it well understood because individuals are not forced to expose their true selves to others while performing malicious attacks. Given the difficulty of interviewing malicious-behaving individuals and the potential untrustworthy nature of their responses, we aim to explore the maliciousness as a human factor through the observable behaviors and attributes of an individual from their actions and interactions with society and networks, but to do so we will need to develop a set of analyzable metrics. The purpose of this paper is twofold: (1) to review human maliciousness-related literature in diverse disciplines (sociology, economics, law, psychology, philosophy, informatics, terrorism, and cybersecurity); and (2) to identify an initial set of proposed assessment metrics and instruments that might be culled from in a future effort to characterize human maliciousness within the cyber realm. The future goal is to integrate these assessment metrics into holistic cybersecurity risk analyses to determine the risk an individual poses to themselves as well as other networks, systems, and/or users.