Close
Distinguished lecture: Deep learning on private data
11 July 2018, 4:00 pm–5:00 pm
In this talk, Prof. Farinaz Koushanfar will discuss their recent results on privacy-preserving frameworks which provides a paradigm shift in efficient deep learning and inference on encrypted data.
Event Information
Open to
- All
Organiser
-
Emiliano De Cristofaro
Location
-
1.03Malet Place Engineering BuildingMalet PlaceLondonWC1E 7JEUnited Kingdom
About
With the ever-increasing volume of data, powerful machine learning models are being developed to efficiently process big data across different applications and industries. On the one hand, the model builder/owners do not want to share the machine learning models as it forms their main intellectual property. On the other hand, applying the model to new user's data which contains sensitive information about individuals raises serious privacy concerns. In this talk, I will discuss our recent results on privacy-preserving frameworks which provides a paradigm shift in efficient deep learning and inference on encrypted data. We provide a comprehensive comparison in terms of unique properties and performances of the recent schemes, and discuss future promising direction.
Visitors from outside UCL please email in advance.
About the Speaker
Prof. Farinaz Koushanfar
Professor and Henry Booker Faculty Scholar at University of California San Diego (UCSD)
Farinaz Koushanfar is a professor and Henry Booker Faculty Scholar in the Electrical and Computer Engineering (ECE) department at University of California San Diego (UCSD), where she directs the Adaptive Computing and Embedded Systems (ACES) Lab. She is the co-founder and co-director of the UCSD Center for Machine-Integrated Computing & Security (MICS). Prof. Koushanfar received her Ph.D. in Electrical Engineering and Computer Science as well as her M.A. in Statistics from UC Berkeley. Her research addresses several aspects of efficient computing and embedded systems, with a focus on hardware and system security, real-time/energy-efficient big data analytics under resource constraints, design automation and synthesis for emerging applications, as well as practical privacy-preserving computing. Professor Koushanfar serves as an associate partner of the Intel Collaborative Research Institute for Secure Computing to aid developing solutions for the next generation of embedded secure devices. Dr. Koushanfar is a fellow of the Kavli Foundation Frontiers of the National Academy of Engineering. She has received a number of awards and honors for her research, mentorship, teaching, and outreach activities including the Presidential Early Career Award for Scientists and Engineers (PECASE) from President Obama, the ACM SIGDA Outstanding New Faculty Award, Cisco IoT Security Grand Challenge Award, MIT Technology Review TR-35 2008 (World’s top 35 innovators under 35), as well as Young Faculty/CAREER Awards from NSF, DARPA, ONR and ARO.