Pilot Class Time: Fridays 2:10-4pm
Pilot Class Location: CSB 480


Data scientists and engineers have significant ethical and legal responsibilities to protect the privacy and best interests of the customers whose data they collect and use. This class discusses these responsibilities, the challenges of meeting them in practice, and a set of advanced technologies that can be used to enhance privacy, accountability, and data protection in big data systems. The focus (and uniqueness) of the class is to look at these technologies with a systems perspective of incorporating them in real data infrastructure systems.

The Spring 2020 version of this class is a pilot one, focusing almost exclusively on differential privacy, a privacy technology that we believe is particularly likely to impact machine learning in the future. In subsequent versions of this class, we plan to incorporate other important privacy technologies: homomorphic databases, secure multi-party computation, and hardware enclaves.

This course will include dedicated lectures that describe the concepts and theory behind these technologies, as well as assigned reading regarding instantiations of these technologies in various algorithms and real-life deployments at Google, Apple, Microsoft, and governmental agencies. The students will also work on a semester-long project that operates at the cutting edge of computer systems research in differential privacy.


Textbook


Grading


Prerequisites:

  1. Security I
  2. COMS W3137 Data Structures and Algorithms
  3. COMS W3157 Advanced Programming