Seminars

View all Seminars  |  Download ICal for this event

How do recommendation systems work? And, what are their privacy implications?

Series: CSA Open Day Keynote talk

Speaker: Prof. Murali Annavaram Rukmini Gopalakrishna Char Visiting Chair Professor Deans Chair Professor in the ECE and CS departments at USC

Date/Time: Mar 04 10:00:00

Location: CSA Seminar Hall (Room No. 254, First Floor)

Abstract:
Have you ever wondered how good Spotify, Netflix, Amazon, .. give you such great recommendations for what to listen, watch, purchase, and live our lives? The magic behind their recommendations are the deep learning machine learning models. These models capture seemingly end-less amounts of information about our online behavior and transform these behaviors into embeddings for future recommendations. These machine learning models are massive (think of terabytes of data), trained on equally imposing set of training samples, called sparse features. Every click, purchase, and even a mouse hover on a website is a sparse feature for training the model. In this talk I will first provide an overview of how current generation recommendation systems work. If these models can recommend so well, then, they must also know a lot about us. In fact, they do. By simply observing features such as click history and object interactions an attacker can de-anonymize users with extremely high probability, or track users across different interaction sessions. For instance, if you tell me what are the last two items you purchased online, I can track you with 97% accuracy. All of which is to say there is a lot of interesting privacy research that needs to get done.

Speaker Bio:
Murali Annavaram is a Deans Chair Professor in the ECE and CS departments at USC. He currently holds the Smt. Rukmini - Shri. Gopalakrishnachar Visiting Chair Professorship at IISc. He is the founding director of the REAL@USC-Meta centre that is focused on research and education in AI, and the co-PI on the NSF DISCoVER Expedition on superconducting computing. His groups KnightShift research won the 2012 IEEE Micro Top Picks most influential research paper award. His work at Intel lead to the first 3D microarchitecture design, and also influenced Intels TurboBoost technology. Murali co-authored Parallel Computer Organization and Design, a widely used textbook in computer architecture. He is a Fellow of IEEE and Senior Member of ACM.

Host Faculty: The Chair, Dept. of CSA