EAGER

This collaborative research between Florida State University and Cornell University is to identify language-action features from text-based messages that can be used to dynamically infer a social actor's perceived trustworthiness. The team will investigate using optimal analysis techniques to calibrate trustworthiness reasoning, which can be used to computationally model actors' deceptive behaviors in cyber space and to infer actors' intent based on their words and actions.

Perhaps the greatest single impediment to the broad adoption of public clouds is concerns about security. Reasoning about all the security aspects of complex modern information systems is enormously difficult. Security is especially problematic in the cloud, where a customer must place their trust in opaque complicated services that they do not understand or control and that are shared with many other customers. Yet, in today's public clouds, the assumption is that providers of cloud services can be fully trusted to provide systems secure against any threat.

Privacy for smartphone and mobile applications users present unprecedented threats. In the United States, privacy policies serve as the primary means to inform users about how mobile apps process privacy data. The application developers are responsible for implementing privacy policies so that the code corresponds to the policies. Currently, there are no techniques for tracing high-level privacy practices into code.

Today, software is making more automated decisions with societal impact. For example, software determines who gets a loan or gets hired, computes risk-assessment scores that help decide who goes to jail and who is set free, and aids in diagnosing and treating medical patients. The increased role of software in such decisions makes software fairness a critical property. As more societal functions operate in cyberspace, the importance of software fairness increases.

In 2016, the cyberthreat landscape showcased advanced attack techniques, escalated attack frequency, and high levels of adversarial sophistication. Conventional cyberattack management is response-driven, with organizations focusing their efforts on detecting threats, rather than anticipating adversarial actions. This reactive approach has limited efficacy, as it does not capture advanced and sophisticated adversaries, mutating or unknown malware, living-off-the-land techniques or new variants being deployed. There is thus an immediate need for a paradigm shift in the area of cybersecurity.