Human/System Co-Design to Protect Data Privacy

Privacy is changing how we build computing systems. Recent regulations (e.g., General Data Protection Regulation) require developers to offer greater privacy protections. However, developers struggle to turn these high-level privacy principles into low-level code implementation. The primary cause of this difficulty is that privacy is a multi-stakeholder issue: developers want to achieve more functionality and productivity; users want more control with lower effort; regulators wish to audit systems with limited resources and do not want to stifle innovation; finally, system deployments need to remain proprietary and efficient. In this talk, I will present a new type of system primitive - Peekaboo - to illustrate that these Human/System requirements must jointly inform system design up-front instead of being afterthoughts. I will describe (1) applying human/system co-design for data minimization, a foundational privacy principle in modern privacy regulation, and (2) how user and other stakeholder experience is transformed in co-designed systems. I will conclude with plans to create a virtuous cycle ecosystem where building trustworthy systems is rewarded, and developers compete to guarantee greater user protection, not less.