Data Privacy in Public Data Sets and Statistical DatabasesSpeaker: RK Shyamasundar – Mumbai, India
Topic(s): Security and Privacy
In the context data privacy laws, there is a need to address the general question of protecting privacy when publicly releasing information about a sensitive dataset. With transactional and historical data sets being available online, privacy attacks have become common. A privacy attack takes seemingly innocuous released information and extracts personal information about individuals. Re-identification attacks are one such class of attacks that leads privacy compromises.
In this talk, we shall review various such attacks such as reconstruction and tracing attacks on statistical databases. We also discuss techniques from the differential privacy literature for releasing approximate aggregate statistics while provably thwarting any privacy attack. It shall further discuss as to how differential privacy comes to rescue and its limitations. We shall also compare it with classical techniques like K-anonymity and its generalizations.
About this LectureNumber of Slides: 75
Duration: 60 minutes
Languages Available: English
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.