My approach to computer security involves formulating the right security problem to work on, addressing design-level issues by constructing strong defenses at the right layer of abstraction, and challenging common assumptions to understand realistic threats. In this talk, I will give several examples of my approach, focusing on emerging technologies that span the digital-to-physical interface. I will cover technical results at various level of abstraction, including design-level vulnerabilities of smart homes, security-oriented improvements to the OAuth network protocol, and optimization-based physical attacks on deep learning models. Finally, I will share my vision of the future of security and privacy research in emerging technologies.
Earlence Fernandes is a research associate at the University of Washington. He formulates and solves emerging problems in computer security using a combination of techniques ranging from threat modeling, measurements, experimental attack analyses, and system design. His current work focuses on the security and privacy issues of emerging technologies, including consumer-facing cyber-physical systems and deep learning systems. Earlence's work has been recognized with two best paper awards (at IEEE Security and Privacy, and IEEE SecDev), has been featured in numerous popular press publications (Wired, Ars Technica, The Verge, Science Magazine), and will be on display as an exhibit at the Science Museum in London. Earlence earned his Ph.D. in Computer Science and Engineering at the University of Michigan in 2017.