Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning Models
- Nathalie Baracaldo Angel
- Farhan Ahmed
- et al.
- 2023
- S&P 2023
Yi Zhou is a Research Staff Member at IBM’s Almaden Research Center in San Jose, CA. Her primary research interests lie in the design of efficient algorithms and techniques for problems that arise in the field of machine learning, federated learning, adversarial machine learning and data security and privacy, etc. More specifically, she worked on building IBM Federated Learning Library and defending against data poisoning attacks for the past few years. Recently, she is also interested in unlearning and data engineering for large language models.
Yi Zhou received her Ph.D. degree from Georgia Institute of Technology in 2018. Her doctoral dissertation focused on designing stochastic algorithms for distributed optimization and machine learning.