This course surveys privacy mechanisms applicable to systems engineering, with a particular focus on the inference threat arising due to advancements in artificial intelligence and machine learning. We will briefly discuss the history of privacy and compare two major examples of general legal frameworks for privacy from the United States and the European Union. We then survey three design frameworks of privacy that may be used to guide the design of privacy-aware information systems. Finally, we survey threat-specific technical privacy frameworks and discuss their applicability in different settings, including statistical privacy with randomized responses, anonymization techniques, semantic privacy models, and technical privacy mechanisms.
Student Learning Outcomes
- Students should be familiar with the different technical paradigms of privacy that are applicable for systems engineering.
- Students should develop critical thinking about the strengths and weaknesses of the different privacy paradigms.
- Students should be able to implement such privacy paradigms, and embed them in information systems during the design process and the implementation phase.
- Students should possess the ability to read literature in the field to stay updated about the state of the art.