Abstract

The quality of learning generally improves with the scale and diversity of data. Companies and institutions can therefore benefit from building models based on shared data. Many cloud and blockchain platforms, as well as government initiatives, are interested in providing this type of service.


These cooperative efforts face a challenge, which we call "exclusivity attacks". A firm can share distorted data, so that it learns the best model fit, but is also able to mislead others. We study protocols for long-term interactions and their vulnerability to these attacks, in particular for regression and clustering tasks. We conclude that the choice of protocol, as well as the number of Sybil identities an attacker may control, is material to the vulnerability of the learning task.

Biography

Yotam Gafni is a fifth-year PhD candidate in Operations Research at Technion, Israel, under the supervision of Prof. Ron Lavi and Prof. Moshe Tennenholtz. He holds a B.A. in Math & Philosophy from the Hebrew University of Jerusalem. His research is focused on the study of incentive mechanism design for data science and economic tasks, through auctions, contests, fair allocation and decision-making, and blockchain systems. List of publications can be found in: https://www.yotamgafni.com/publications

• Admission

Zoom Meeting ID: 836 4744 4173
Passcode: 456950