USC + Amazon Center on Secure and Trusted Machine Learning selects five new research projects
Faculty projects are focused on various aspects of trustworthy machine learning.
The USC + Amazon Center on Secure and Trusted Machine Learning today announced it has selected five new faculty research projects for 2022-2023.
The center was established in January 2021 to support fundamental research and development of new approaches to machine learning (ML) privacy, security, and trustworthiness.
“For our second year, we have launched an exciting set of projects focusing on various aspects of trustworthy machine learning,” said Salman Avestimehr, the center’s director and professor of electrical and computer engineering and computer science. “These are particularly focused on privacy-preserving approaches via federated learning and secure aggregation, explainability and fairness in complex machine learning models, human-centered designs of machine learning systems, and security of the underlying infrastructure.”
Below are the research award recipients and details on their projects:
- Urbashi Mitra, Gordon S. Marshall Chair in Engineering and professor of electrical and computer engineering and computer science: “Bilinear mechanisms for physical layer security in the Internet of Things”.
- Shrikanth Narayanan, the Niki & C. L. Max Nikias Chair in Engineering and professor of electrical and computer engineering and computer science: “Federated learning for human-centered experience and perception modeling with bio-behavioral data”.
- Antonio Ortega, professor of electrical and computer engineering: “Deep learning and data geometry: A data-driven graph framework for explainable and trustworthy AI.”
- Konstantinos Psounis, professor of electrical and computer engineering and computer science: “Federated learning with secure aggregation: Accessing and improving its privacy”.
- Meisam Razaviyayn, assistant professor of industrial and systems engineering, electrical and computer engineering, and computer science: “Fair federated learning with private access to sensitive features”.
“We are excited by the high quality of research proposals from USC faculty,” said Prem Natarajan, Alexa AI vice president. “The five projects that have been selected for funding in this second year of our partnership with USC represent a deepening and broadening of collective vision for the USC-Amazon Center on Secure and Trusted Machine Learning.”
“The research results during the first year of the USC-Amazon partnership have been impressive, covering many different fields, from bio-behavioral data to explainable and trustworthy AI to applications on the Internet of Things,” said Yannis C. Yortsos, Dean of the USC Viterbi School of Engineering. “We look forward to continuing and further enhancing our partnership for the benefit of our students, for advancing thought leadership, and for a positive impact on society at large.”