Publications

Where possible, we want to investigate how existing technology and/or telemetry could be used to address key issues pertaining to vulnerable populations. In addition, we want to develop new techniques to try and solve specific problems in the areas of abuse, scams, and child online safety.

The tremendous growth in the learning capacity of Machine Learning methods has yet to be met with a corresponding growth in our ability to understand these models. Equally troubling, our ability to build robust machine learning models has not kept pace with research in adversarial attacks against machine learning. As we increasingly hand over decision making to automated machine learning and AI systems, we must find ways that the life-altering decisions made by these systems can be audited for fairness, safety, robustness to adversaries, and the preservation of privacy of any personally identifiable information over which they operate.

There is a continual need for security systems of many kinds, including traditional endpoints, mobile devices, cloud, IoT and virtual hosts. The continual evolution of these computing platforms results in new threats, but also in opportunities to better secure these systems. Furthermore, widespread deployment of trusted hardware brings new opportunities, but also a set of hardware-level threats that are not easily mitigated. The escalating cost of data breaches continues to make defending sensitive data a priority, and enterprises are becoming increasingly open to adopting new classes of defenses and encryption-based solutions to prevent serious breaches.