Hai Phan Authors Book to Provide Insights into Trustworthy Federated Learning

Associate Professor Hai Phan in Ying Wu College of Computing's Department of Data Science, and a pioneer in Trustworthy AI, has recently co-authored a handbook that will guide anyone from expert to beginner who seeks to venture into the realms of trustworthy federated learning.

"Handbook of Trustworthy Federated Learning" is published by Springer Publishing, a leading source of health care books, textbooks and medical journals for medical professionals, professors and universities, is co-authored by My T. Thai, research foundation professor in the department of Computer & Information Science & Engineering at the University of Florida, and Bhavani Thuraisingham, founders chair professor of computer science at the University of Texas at Dallas.

The book aims to be a "one-stop, reliable resource, including curated surveys and expository contributions on federated learning." It covers a comprehensive range of topics that combine technical and non-technical fundamentals, applications and extensive details of various topics.

First introduced in 2016, federated learning allows devices to collaboratively learn a shared model while keeping raw data localized to protect data privacy. Federated learning can enable myriad applications in practice, from health care and crime detection to human sensing based on mobile signals, among many others, without the prohibitive cost of privacy, security and administrative procedures of centralized data integration.

However, as Phan remarked in an earlier article recognizing a $740,000 grant to develop a trustworthy FL model to address new standards in AI safety and security, "Technology has advanced to a non-coding model that enables the general public to use AI in their everyday lives. However, if concerns over security and privacy prevent this, such advances are meaningless."

Phan and his collaborators spent the last one and a half years writing what they anticipate will be a "steppingstone" to broaden the future direction of optimizing privacy and security through the discovery and enhancement of large language models, while also helping to influence a greener carbon footprint.

He has also created a course in federated machine learning, which will be offered in spring 2025.

The "Handbook of Trustworthy Federated Learning" may be pre-ordered prior to its official release date of Aug. 25, 2024 through Springer Publishing or Barnes & Noble.